Common Weakness Enumeration

CWE-367

Allowed

Time-of-check Time-of-use (TOCTOU) Race Condition

Abstraction: Base · Status: Incomplete

API response cwe.mitre.org

The product checks the state of a resource before using that resource, but the resource's state can change between the check and the use in a way that invalidates the results of the check.

1328 vulnerabilities reference this CWE, most recent first.

GHSA-CHCM-JQP3-J5W3

Vulnerability from github – Published: 2025-12-18 21:31 – Updated: 2026-01-15 21:31
VLAI
Details

BullWall Server Intrusion Protection services are initialized after login services. An authenticated attacker with administrative permissions can log in after boot and bypass MFA. SIP service does not retroactively enforce the challenge or disconnect unauthenticated sessions. Versions 4.6.0.0, 4.6.0.6, 4.6.0.7, and 4.6.1.4 were confirmed to be affected; other versions before and after may also be affected.

Severity
6.2 (Medium)
CVSS:3.1/AV:N/AC:H/PR:H/UI:N/S:U/C:H/I:H/A:L
7.5 (High)
CVSS:4.0/AV:N/AC:L/AT:P/PR:H/UI:N/VC:H/VI:H/VA:L/SC:N/SI:N/SA:N
Show details on source website
To clipboard 

{
  "affected": [],
  "aliases": [
    "CVE-2025-62004"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-367"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2025-12-18T21:15:54Z",
    "severity": "HIGH"
  },
  "details": "BullWall Server Intrusion Protection services are initialized after login services. An authenticated attacker with administrative permissions can log in after boot and bypass MFA. SIP service does not retroactively enforce the challenge or disconnect unauthenticated sessions. Versions 4.6.0.0, 4.6.0.6, 4.6.0.7, and 4.6.1.4 were confirmed to be affected; other versions before and after may also be affected.",
  "id": "GHSA-chcm-jqp3-j5w3",
  "modified": "2026-01-15T21:31:42Z",
  "published": "2025-12-18T21:31:44Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2025-62004"
    },
    {
      "type": "WEB",
      "url": "https://raw.githubusercontent.com/cisagov/CSAF/develop/csaf_files/IT/white/2025/VA-25-352-01.json"
    },
    {
      "type": "WEB",
      "url": "https://www.cve.org/CVERecord?id=CVE-2025-62004"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:H/PR:H/UI:N/S:U/C:H/I:H/A:L",
      "type": "CVSS_V3"
    },
    {
      "score": "CVSS:4.0/AV:N/AC:L/AT:P/PR:H/UI:N/VC:H/VI:H/VA:L/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X",
      "type": "CVSS_V4"
    }
  ]
}

GHSA-CJF9-9CPV-7XR2

Vulnerability from github – Published: 2022-05-24 17:49 – Updated: 2022-05-24 17:49
VLAI
Details

This vulnerability allows local attackers to escalate privileges on affected installations of Parallels Desktop 16.1.1-49141. An attacker must first obtain the ability to execute high-privileged code on the target guest system in order to exploit this vulnerability. The specific flaw exists within the e1000e virtual device. The issue results from the lack of proper locking when performing operations on an object. An attacker can leverage this vulnerability to escalate privileges and execute arbitrary code in the context of the hypervisor. Was ZDI-CAN-12527.

Show details on source website
To clipboard 

{
  "affected": [],
  "aliases": [
    "CVE-2021-31422"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-367"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2021-04-29T17:15:00Z",
    "severity": "HIGH"
  },
  "details": "This vulnerability allows local attackers to escalate privileges on affected installations of Parallels Desktop 16.1.1-49141. An attacker must first obtain the ability to execute high-privileged code on the target guest system in order to exploit this vulnerability. The specific flaw exists within the e1000e virtual device. The issue results from the lack of proper locking when performing operations on an object. An attacker can leverage this vulnerability to escalate privileges and execute arbitrary code in the context of the hypervisor. Was ZDI-CAN-12527.",
  "id": "GHSA-cjf9-9cpv-7xr2",
  "modified": "2022-05-24T17:49:11Z",
  "published": "2022-05-24T17:49:11Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2021-31422"
    },
    {
      "type": "WEB",
      "url": "https://kb.parallels.com/en/125013"
    },
    {
      "type": "WEB",
      "url": "https://www.zerodayinitiative.com/advisories/ZDI-21-430"
    }
  ],
  "schema_version": "1.4.0",
  "severity": []
}

GHSA-CM76-QM8V-3J95

Vulnerability from github – Published: 2025-05-21 16:53 – Updated: 2025-05-28 19:44
VLAI
Summary
containerd allows host filesystem access on pull
Details

Impact

A time-of-check to time-of-use (TOCTOU) vulnerability was found in containerd v2.1.0. While unpacking an image during an image pull, specially crafted container images could arbitrarily modify the host file system.

Patches

This bug has been fixed in the following containerd versions:

  • 2.1.1

The only affected version of containerd is 2.1.0. Other versions of containerd are not affected.

Users should update to this version to resolve the issue.

Workarounds

Ensure that only trusted images are used and that only trusted users have permissions to import images.

Credits

The containerd project would like to thank Tõnis Tiigi for responsibly disclosing this issue in accordance with the containerd security policy.

References

https://cve.mitre.org/cgi-bin/cvename.cgi?name=CVE-2025-47290

For more information

If you have any questions or comments about this advisory:

To report a security issue in containerd:

Severity
7.6 (High)
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:A/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H/E:U
Show details on source website
To clipboard 

{
  "affected": [
    {
      "package": {
        "ecosystem": "Go",
        "name": "github.com/containerd/containerd/v2"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "2.1.0"
            },
            {
              "fixed": "2.1.1"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2025-47290"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-367"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2025-05-21T16:53:09Z",
    "nvd_published_at": "2025-05-20T19:15:50Z",
    "severity": "HIGH"
  },
  "details": "### Impact\n\nA time-of-check to time-of-use (TOCTOU) vulnerability was found in containerd v2.1.0. While unpacking an image during an image pull, specially crafted container images could arbitrarily modify the host file system. \n\n### Patches\nThis bug has been fixed in the following containerd versions:\n\n* 2.1.1\n\nThe only affected version of containerd is 2.1.0.  Other versions of containerd are not affected.\n\nUsers should update to this version to resolve the issue.\n\n### Workarounds\nEnsure that only trusted images are used and that only trusted users have permissions to import images.\n\n### Credits\nThe containerd project would like to thank T\u00f5nis Tiigi for responsibly disclosing this issue in accordance with the [containerd security policy](https://github.com/containerd/project/blob/main/SECURITY.md).\n\n### References\nhttps://cve.mitre.org/cgi-bin/cvename.cgi?name=CVE-2025-47290\n\n### For more information\nIf you have any questions or comments about this advisory:\n\n* Open an issue in [containerd](https://github.com/containerd/containerd/issues/new/choose)\n* Email us at [security@containerd.io](mailto:security@containerd.io)\n\nTo report a security issue in containerd:\n\n* [Report a new vulnerability](https://github.com/containerd/containerd/security/advisories/new)\n* Email us at [security@containerd.io](mailto:security@containerd.io)",
  "id": "GHSA-cm76-qm8v-3j95",
  "modified": "2025-05-28T19:44:10Z",
  "published": "2025-05-21T16:53:09Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/containerd/containerd/security/advisories/GHSA-cm76-qm8v-3j95"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2025-47290"
    },
    {
      "type": "WEB",
      "url": "https://github.com/containerd/containerd/commit/cada13298fba85493badb6fecb6ccf80e49673cc"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/containerd/containerd"
    },
    {
      "type": "WEB",
      "url": "https://github.com/containerd/containerd/releases/tag/v2.1.1"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:A/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H/E:U",
      "type": "CVSS_V4"
    }
  ],
  "summary": "containerd allows host filesystem access on pull"
}

GHSA-CMHJ-WH2F-9CGX

Vulnerability from github – Published: 2026-09-23 18:12 – Updated: 2026-09-23 18:12
VLAI
Summary
9router: Image prefetch DNS rebinding allows SSRF to internal services
Details

Summary

9router validates image URLs by resolving the host before fetching, but the later server-side fetch performs a separate DNS resolution. An attacker-controlled DNS name can resolve to a public IP during validation and then rebind to an internal Docker/private IP during the fetch. This allows the server-side image prefetch to reach internal-only HTTP services (SSRF).

Details

  • Affected version / commit: 9router v0.4.80 @ b282f05.
  • Reachable through /v1/chat/completions with a vision-capable model and an image_url content part. A vision-capable model name is required so the image survives modality stripping and the server-side prefetch is armed.
  • The provider used in this reproduction is the bundled mock provider — no real API key and no real provider call.
  • internal-admin (the SSRF target) is not exposed to the host network; it is reachable only from inside the Docker network.
  • rebind-dns behaviour for rebind.9r.test:
  • first A response → 1.1.1.1 (public) to pass the public-host guard,
  • second A response → 172.29.0.10 (internal-admin) during the fetch.
  • internal-admin logs GET /ssrf-marker with peer=172.29.0.30 (the proxied-router container), proving the server-side fetch landed on the internal service.
  • mock-provider receives POST /api/chat and the flow completes with HTTP 200.
  • Root cause: DNS TOCTOU — the IP is not pinned between the validation resolution (the public-host guard) and the fetch resolution. The guard and the fetch each resolve the hostname independently, so a TTL-0 rebinding authority can return a public IP to the guard and an internal IP to the fetch.

Proof of Concept

This repository is a self-contained Docker Compose reproduction. No real provider is called and no real API key is required.

  1. Build and start the stack: bash docker compose up --build
  2. Confirm internal-admin is unreachable from the host: bash curl -i http://127.0.0.1:18083/ssrf-marker # connection refused / fail docker compose ps # internal-admin has NO host port mapping
  3. Send the request named POST image-prefetch DNS rebinding trigger from requests.http, or with curl: bash curl -i -X POST http://127.0.0.1:18082/v1/chat/completions \ -H "Content-Type: application/json" \ -d '{ "model": "ollama-local/gemma3", "messages": [{"role":"user","content":[ {"type":"text","text":"reproduction image-prefetch trigger"}, {"type":"image_url","image_url":{"url":"http://rebind.9r.test:8080/ssrf-marker?case=rebind-trigger"}} ]}], "stream": false }'

Impact

  • SSRF to internal HTTP services reachable from the 9router host/container.
  • Depending on the environment, this can reach cloud metadata endpoints, internal admin panels, or be used for internal service discovery.
  • Blind / semi-blind SSRF when the fetched response is not returned to the attacker; an exfil variant (pointing the image at an internal endpoint that returns valid image bytes) can return internal content base64-encoded to the upstream.
  • Requires a code path that prefetches/normalizes remote images for vision-capable providers.
  • No real credential is needed for the reproduction.

Suggested Fix

  • Pin the resolved IP after validation and connect to that IP (resolve once, then reuse the address for the fetch).
  • Block private, loopback, link-local, multicast, and cloud-metadata ranges at connect time, not only at validation time.
  • Perform DNS resolution and IP checks immediately before the request and against the address actually used to connect.
  • Disable redirects, or re-validate every redirect target with the same checks.
  • Enforce an allowlist for image-fetch domains where feasible.
  • Add a timeout, a response size limit, and a content-type check.
Severity
7.4 (High)
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:L/I:L/A:L
Show details on source website
To clipboard 

{
  "affected": [
    {
      "database_specific": {
        "last_known_affected_version_range": "\u003c= 0.4.80"
      },
      "package": {
        "ecosystem": "npm",
        "name": "9router"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "0.5.2"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-56676"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-367",
      "CWE-918"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-09-23T18:12:28Z",
    "nvd_published_at": "2026-07-10T16:16:34Z",
    "severity": "HIGH"
  },
  "details": "## Summary\n\n9router validates image URLs by resolving the host before fetching, but the later\nserver-side fetch performs a separate DNS resolution. An attacker-controlled DNS name can\nresolve to a public IP during validation and then rebind to an internal Docker/private IP\nduring the fetch. This allows the server-side image prefetch to reach internal-only HTTP\nservices (SSRF).\n\n## Details\n\n- **Affected version / commit:** 9router `v0.4.80` @ `b282f05`.\n- **Reachable through** `/v1/chat/completions` with a **vision-capable model** and an\n  `image_url` content part. A vision-capable model name is required so the image survives\n  modality stripping and the server-side prefetch is armed.\n- The provider used in this reproduction is the bundled **mock provider** \u2014 **no real API\n  key and no real provider call**.\n- **internal-admin** (the SSRF target) is **not exposed to the host network**; it is\n  reachable only from inside the Docker network.\n- **rebind-dns** behaviour for `rebind.9r.test`:\n  - first A response \u2192 `1.1.1.1` (public) to pass the public-host guard,\n  - second A response \u2192 `172.29.0.10` (internal-admin) during the fetch.\n- **internal-admin** logs `GET /ssrf-marker` with `peer=172.29.0.30` (the `proxied-router`\n  container), proving the server-side fetch landed on the internal service.\n- **mock-provider** receives `POST /api/chat` and the flow completes with `HTTP 200`.\n- **Root cause:** DNS TOCTOU \u2014 the IP is **not pinned** between the validation resolution\n  (the public-host guard) and the fetch resolution. The guard and the fetch each resolve the\n  hostname independently, so a TTL-0 rebinding authority can return a public IP to the guard\n  and an internal IP to the fetch.\n\n## Proof of Concept\n\nThis repository is a self-contained Docker Compose reproduction. No real provider is called\nand no real API key is required.\n\n1. Build and start the stack:\n   ```bash\n   docker compose up --build\n   ```\n2. Confirm `internal-admin` is unreachable from the host:\n   ```bash\n   curl -i http://127.0.0.1:18083/ssrf-marker   # connection refused / fail\n   docker compose ps                            # internal-admin has NO host port mapping\n   ```\n3. Send the request named **`POST image-prefetch DNS rebinding trigger`** from\n   [`requests.http`](./requests.http), or with curl:\n   ```bash\n   curl -i -X POST http://127.0.0.1:18082/v1/chat/completions \\\n     -H \"Content-Type: application/json\" \\\n     -d \u0027{\n       \"model\": \"ollama-local/gemma3\",\n       \"messages\": [{\"role\":\"user\",\"content\":[\n         {\"type\":\"text\",\"text\":\"reproduction image-prefetch trigger\"},\n         {\"type\":\"image_url\",\"image_url\":{\"url\":\"http://rebind.9r.test:8080/ssrf-marker?case=rebind-trigger\"}}\n       ]}],\n       \"stream\": false\n     }\u0027\n   ```\n\n## Impact\n\n- SSRF to internal HTTP services reachable from the 9router host/container.\n- Depending on the environment, this can reach cloud metadata endpoints, internal admin\n  panels, or be used for internal service discovery.\n- Blind / semi-blind SSRF when the fetched response is not returned to the attacker; an\n  exfil variant (pointing the image at an internal endpoint that returns valid image bytes)\n  can return internal content base64-encoded to the upstream.\n- Requires a code path that prefetches/normalizes remote images for vision-capable\n  providers.\n- No real credential is needed for the reproduction.\n\n## Suggested Fix\n\n- **Pin the resolved IP** after validation and connect to **that** IP (resolve once, then\n  reuse the address for the fetch).\n- Block private, loopback, link-local, multicast, and cloud-metadata ranges **at connect\n  time**, not only at validation time.\n- Perform DNS resolution and IP checks immediately before the request and against the\n  address actually used to connect.\n- Disable redirects, or re-validate every redirect target with the same checks.\n- Enforce an allowlist for image-fetch domains where feasible.\n- Add a timeout, a response size limit, and a content-type check.",
  "id": "GHSA-cmhj-wh2f-9cgx",
  "modified": "2026-09-23T18:12:28Z",
  "published": "2026-09-23T18:12:28Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/decolua/9router/security/advisories/GHSA-cmhj-wh2f-9cgx"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-56676"
    },
    {
      "type": "WEB",
      "url": "https://github.com/decolua/9router/commit/c7d07448c58bec1200741de0b73305b860416b82"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/decolua/9router"
    },
    {
      "type": "WEB",
      "url": "https://github.com/decolua/9router/releases/tag/v0.5.2"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:L/I:L/A:L",
      "type": "CVSS_V3"
    }
  ],
  "summary": "9router: Image prefetch DNS rebinding allows SSRF to internal services"
}

GHSA-CMRH-WVQ6-WM9R

Vulnerability from github – Published: 2026-05-08 16:59 – Updated: 2026-05-13 13:35
VLAI
Summary
n8n-mcp webhook and API client paths has an authenticated SSRF
Details

Summary

Authenticated Server-Side Request Forgery affecting the webhook trigger tools, the n8n API client (N8N_API_URL), and per-request URLs supplied via the x-n8n-url header in multi-tenant HTTP mode.

Impact

A caller with access to the MCP session can drive HTTP requests from the n8n-mcp host to internal services and cloud metadata endpoints that the SSRF gate is meant to block. The response body is returned to the caller, making internal-service enumeration and credential theft immediate without any out-of-band channel.

  • Multi-tenant HTTP deployments where tenants share an AUTH_TOKEN: any tenant with valid credentials can reach the operator's cloud metadata service and exfiltrate temporary IAM / GCP service account / Azure managed-identity credentials.
  • Single-tenant deployments: indirect prompt injection through tool arguments reaches the same surface; an attacker who can influence the LLM's tool calls can read internal services from the n8n-mcp host.
  • Stdio deployments are reachable via the same prompt-injection path.

Patched Versions

Fixed in n8n-mcp@2.50.2.

Note for operators: The same SSRF gate that previously covered webhook URLs now also covers the n8n API client base URL. If N8N_API_URL points at http://localhost:5678 (n8n on the same host) or an RFC1918 address (n8n on the same private network), set WEBHOOK_SECURITY_MODE=moderate (allows localhost, still blocks RFC1918 and cloud metadata) or WEBHOOK_SECURITY_MODE=permissive (allows RFC1918 too — only safe on a trusted private network). Default strict is correct for deployments where n8n is reachable at a public hostname.

Workarounds

For deployments that cannot upgrade immediately:

  1. Restrict network egress from the n8n-mcp host with a firewall, reverse proxy, or cloud security group. Explicitly deny cloud metadata IPs (169.254.169.254, 169.254.170.2, 100.100.100.200, 192.0.0.192, and the GCP metadata.google.internal resolved IP) and any RFC1918 networks the server does not legitimately need to reach.
  2. Run in stdio mode instead of HTTP if the multi-tenant surface is not needed (no shared AUTH_TOKEN to compromise).
  3. Disable workflow management tools via DISABLED_TOOLS=n8n_trigger_webhook_workflow,n8n_create_workflow,n8n_test_workflow if the deployment does not need them.

Credit

Reported by @fg0x0.

Severity
7.2 (High)
CVSS:4.0/AV:N/AC:H/AT:P/PR:L/UI:N/VC:H/VI:L/VA:L/SC:H/SI:L/SA:L
Show details on source website
To clipboard 

{
  "affected": [
    {
      "package": {
        "ecosystem": "npm",
        "name": "n8n-mcp"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "2.18.7"
            },
            {
              "fixed": "2.50.2"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-44694"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-367",
      "CWE-918"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-05-08T16:59:17Z",
    "nvd_published_at": "2026-05-08T20:16:31Z",
    "severity": "HIGH"
  },
  "details": "### Summary\n\nAuthenticated Server-Side Request Forgery affecting the webhook trigger tools, the n8n API client (`N8N_API_URL`), and per-request URLs supplied via the `x-n8n-url` header in multi-tenant HTTP mode.\n\n### Impact\n\nA caller with access to the MCP session can drive HTTP requests from the n8n-mcp host to internal services and cloud metadata endpoints that the SSRF gate is meant to block. The response body is returned to the caller, making internal-service enumeration and credential theft immediate without any out-of-band channel.\n\n- **Multi-tenant HTTP deployments** where tenants share an `AUTH_TOKEN`: any tenant with valid credentials can reach the operator\u0027s cloud metadata service and exfiltrate temporary IAM / GCP service account / Azure managed-identity credentials.\n- **Single-tenant deployments**: indirect prompt injection through tool arguments reaches the same surface; an attacker who can influence the LLM\u0027s tool calls can read internal services from the n8n-mcp host.\n- **Stdio deployments** are reachable via the same prompt-injection path.\n\n### Patched Versions\n\nFixed in `n8n-mcp@2.50.2`.\n\n**Note for operators:** The same SSRF gate that previously covered webhook URLs now also covers the n8n API client base URL. If `N8N_API_URL` points at `http://localhost:5678` (n8n on the same host) or an RFC1918 address (n8n on the same private network), set `WEBHOOK_SECURITY_MODE=moderate` (allows localhost, still blocks RFC1918 and cloud metadata) or `WEBHOOK_SECURITY_MODE=permissive` (allows RFC1918 too \u2014 only safe on a trusted private network). Default `strict` is correct for deployments where n8n is reachable at a public hostname.\n\n### Workarounds\n\nFor deployments that cannot upgrade immediately:\n\n1. **Restrict network egress** from the n8n-mcp host with a firewall, reverse proxy, or cloud security group. Explicitly deny cloud metadata IPs (`169.254.169.254`, `169.254.170.2`, `100.100.100.200`, `192.0.0.192`, and the GCP `metadata.google.internal` resolved IP) and any RFC1918 networks the server does not legitimately need to reach.\n2. **Run in stdio mode** instead of HTTP if the multi-tenant surface is not needed (no shared `AUTH_TOKEN` to compromise).\n3. **Disable workflow management tools** via `DISABLED_TOOLS=n8n_trigger_webhook_workflow,n8n_create_workflow,n8n_test_workflow` if the deployment does not need them.\n\n### Credit\n\nReported by [@fg0x0](https://github.com/fg0x0).",
  "id": "GHSA-cmrh-wvq6-wm9r",
  "modified": "2026-05-13T13:35:05Z",
  "published": "2026-05-08T16:59:17Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/czlonkowski/n8n-mcp/security/advisories/GHSA-cmrh-wvq6-wm9r"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-44694"
    },
    {
      "type": "WEB",
      "url": "https://github.com/czlonkowski/n8n-mcp/commit/bcaba839409d470abeb4a6ad9b361b553a1098eb"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/czlonkowski/n8n-mcp"
    },
    {
      "type": "WEB",
      "url": "https://github.com/czlonkowski/n8n-mcp/releases/tag/v2.50.2"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:4.0/AV:N/AC:H/AT:P/PR:L/UI:N/VC:H/VI:L/VA:L/SC:H/SI:L/SA:L",
      "type": "CVSS_V4"
    }
  ],
  "summary": "n8n-mcp webhook and API client paths has an authenticated SSRF"
}

GHSA-CP3Q-Q6MX-W79J

Vulnerability from github – Published: 2023-08-02 15:30 – Updated: 2024-01-12 09:30
VLAI
Details

External service lookups for a number of protocols were vulnerable to a time-of-check/time-of-use (TOCTOU) weakness, involving the JDK DNS cache. Attackers that were timing DNS cache expiry correctly were able to inject configuration that would bypass existing network deny-lists. Attackers could exploit this weakness to discover the existence of restricted network infrastructure and service availability. Improvements were made to include deny-lists not only during the check of the provided connection data, but also during use. No publicly available exploits are known.

Severity
4.3 (Medium)
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:N
Show details on source website
To clipboard 

{
  "affected": [],
  "aliases": [
    "CVE-2023-26438"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-367",
      "CWE-918"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2023-08-02T13:15:10Z",
    "severity": "LOW"
  },
  "details": "External service lookups for a number of protocols were vulnerable to a time-of-check/time-of-use (TOCTOU) weakness, involving the JDK DNS cache. Attackers that were timing DNS cache expiry correctly were able to inject configuration that would bypass existing network deny-lists. Attackers could exploit this weakness to discover the existence of restricted network infrastructure and service availability. Improvements were made to include deny-lists not only during the check of the provided connection data, but also during use. No publicly available exploits are known.\n\n",
  "id": "GHSA-cp3q-q6mx-w79j",
  "modified": "2024-01-12T09:30:27Z",
  "published": "2023-08-02T15:30:52Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2023-26438"
    },
    {
      "type": "WEB",
      "url": "https://documentation.open-xchange.com/appsuite/security/advisories/csaf/2023/oxas-adv-2023-0003.json"
    },
    {
      "type": "WEB",
      "url": "https://documentation.open-xchange.com/security/advisories/csaf/oxas-adv-2023-0003.json"
    },
    {
      "type": "WEB",
      "url": "https://software.open-xchange.com/products/appsuite/doc/Release_Notes_for_Patch_Release_6230_7.10.6_2023-05-02.pdf"
    },
    {
      "type": "WEB",
      "url": "http://packetstormsecurity.com/files/173943/OX-App-Suite-SSRF-SQL-Injection-Cross-Site-Scripting.html"
    },
    {
      "type": "WEB",
      "url": "http://seclists.org/fulldisclosure/2023/Aug/8"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:N",
      "type": "CVSS_V3"
    }
  ]
}

GHSA-CP85-4PFJ-F5QQ

Vulnerability from github – Published: 2022-05-13 01:53 – Updated: 2022-05-13 01:53
VLAI
Details

An elevation of privilege vulnerability exists when Windows improperly handles calls to Advanced Local Procedure Call (ALPC), aka "Windows ALPC Elevation of Privilege Vulnerability." This affects Windows Server 2016, Windows 10, Windows Server 2019, Windows 10 Servers.

Severity
7.8 (High)
CVSS:3.0/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Show details on source website
To clipboard 

{
  "affected": [],
  "aliases": [
    "CVE-2018-8584"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-367"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2018-11-14T01:29:00Z",
    "severity": "HIGH"
  },
  "details": "An elevation of privilege vulnerability exists when Windows improperly handles calls to Advanced Local Procedure Call (ALPC), aka \"Windows ALPC Elevation of Privilege Vulnerability.\" This affects Windows Server 2016, Windows 10, Windows Server 2019, Windows 10 Servers.",
  "id": "GHSA-cp85-4pfj-f5qq",
  "modified": "2022-05-13T01:53:46Z",
  "published": "2022-05-13T01:53:46Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2018-8584"
    },
    {
      "type": "WEB",
      "url": "https://portal.msrc.microsoft.com/en-US/security-guidance/advisory/CVE-2018-8584"
    },
    {
      "type": "WEB",
      "url": "https://www.exploit-db.com/exploits/46104"
    },
    {
      "type": "WEB",
      "url": "http://www.securityfocus.com/bid/105808"
    },
    {
      "type": "WEB",
      "url": "http://www.securitytracker.com/id/1042119"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.0/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H",
      "type": "CVSS_V3"
    }
  ]
}

GHSA-CQPW-MC9F-6GF5

Vulnerability from github – Published: 2022-05-24 17:32 – Updated: 2022-05-24 17:32
VLAI
Details

A race condition was addressed with additional validation. This issue is fixed in macOS Catalina 10.15.6. A malicious application may be able to execute arbitrary code with kernel privileges.

Severity
7.8 (High)
CVSS:3.1/AV:L/AC:H/PR:L/UI:N/S:C/C:H/I:H/A:H
Show details on source website
To clipboard 

{
  "affected": [],
  "aliases": [
    "CVE-2020-9990"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-362",
      "CWE-367"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2020-10-22T19:15:00Z",
    "severity": "HIGH"
  },
  "details": "A race condition was addressed with additional validation. This issue is fixed in macOS Catalina 10.15.6. A malicious application may be able to execute arbitrary code with kernel privileges.",
  "id": "GHSA-cqpw-mc9f-6gf5",
  "modified": "2022-05-24T17:32:09Z",
  "published": "2022-05-24T17:32:09Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2020-9990"
    },
    {
      "type": "WEB",
      "url": "https://support.apple.com/kb/HT211289"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:L/AC:H/PR:L/UI:N/S:C/C:H/I:H/A:H",
      "type": "CVSS_V3"
    }
  ]
}

GHSA-CRRX-464G-PWJ8

Vulnerability from github – Published: 2026-07-14 18:32 – Updated: 2026-07-14 18:32
VLAI
Details

Time-of-check time-of-use (toctou) race condition in Microsoft Defender allows an authorized attacker to elevate privileges locally.

Severity
7.0 (High)
CVSS:3.1/AV:L/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:H
Show details on source website
To clipboard 

{
  "affected": [],
  "aliases": [
    "CVE-2026-50658"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-367"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2026-07-14T18:17:59Z",
    "severity": "HIGH"
  },
  "details": "Time-of-check time-of-use (toctou) race condition in Microsoft Defender allows an authorized attacker to elevate privileges locally.",
  "id": "GHSA-crrx-464g-pwj8",
  "modified": "2026-07-14T18:32:29Z",
  "published": "2026-07-14T18:32:28Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-50658"
    },
    {
      "type": "WEB",
      "url": "https://msrc.microsoft.com/update-guide/vulnerability/CVE-2026-50658"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:L/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:H",
      "type": "CVSS_V3"
    }
  ]
}

GHSA-CRV2-V9HJ-XFFJ

Vulnerability from github – Published: 2025-08-12 18:31 – Updated: 2025-08-12 18:31
VLAI
Details

Time-of-check time-of-use (toctou) race condition in Windows NTFS allows an unauthorized attacker to disclose information locally.

Severity
7.0 (High)
CVSS:3.1/AV:L/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H
Show details on source website
To clipboard 

{
  "affected": [],
  "aliases": [
    "CVE-2025-50158"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-367"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2025-08-12T18:15:32Z",
    "severity": "HIGH"
  },
  "details": "Time-of-check time-of-use (toctou) race condition in Windows NTFS allows an unauthorized attacker to disclose information locally.",
  "id": "GHSA-crv2-v9hj-xffj",
  "modified": "2025-08-12T18:31:30Z",
  "published": "2025-08-12T18:31:30Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2025-50158"
    },
    {
      "type": "WEB",
      "url": "https://msrc.microsoft.com/update-guide/vulnerability/CVE-2025-50158"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:L/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H",
      "type": "CVSS_V3"
    }
  ]
}
Mitigation
Implementation

The most basic advice for TOCTOU vulnerabilities is to not perform a check before the use. This does not resolve the underlying issue of the execution of a function on a resource whose state and identity cannot be assured, but it does help to limit the false sense of security given by the check.

Mitigation
Implementation

When the file being altered is owned by the current user and group, set the effective gid and uid to that of the current user and group when executing this statement.

Mitigation
Architecture and Design

Limit the interleaving of operations on files from multiple processes.

Mitigation
Implementation Architecture and Design

If you cannot perform operations atomically and you must share access to the resource between multiple processes or threads, then try to limit the amount of time (CPU cycles) between the check and use of the resource. This will not fix the problem, but it could make it more difficult for an attack to succeed.

Mitigation
Implementation

Recheck the resource after the use call to verify that the action was taken appropriately.

Mitigation
Architecture and Design

Ensure that some environmental locking mechanism can be used to protect resources effectively.

Mitigation
Implementation

Ensure that locking occurs before the check, as opposed to afterwards, such that the resource, as checked, is the same as it is when in use.

CAPEC-27: Leveraging Race Conditions via Symbolic Links

This attack leverages the use of symbolic links (Symlinks) in order to write to sensitive files. An attacker can create a Symlink link to a target file not otherwise accessible to them. When the privileged program tries to create a temporary file with the same name as the Symlink link, it will actually write to the target file pointed to by the attackers' Symlink link. If the attacker can insert malicious content in the temporary file they will be writing to the sensitive file by using the Symlink. The race occurs because the system checks if the temporary file exists, then creates the file. The attacker would typically create the Symlink during the interval between the check and the creation of the temporary file.

CAPEC-29: Leveraging Time-of-Check and Time-of-Use (TOCTOU) Race Conditions

This attack targets a race condition occurring between the time of check (state) for a resource and the time of use of a resource. A typical example is file access. The adversary can leverage a file access race condition by "running the race", meaning that they would modify the resource between the first time the target program accesses the file and the time the target program uses the file. During that period of time, the adversary could replace or modify the file, causing the application to behave unexpectedly.

← Back to the CWE list