GHSA-M9MQ-7M7Q-XC6P

Vulnerability from github – Published: 2026-08-25 16:28 – Updated: 2026-08-25 16:28
VLAI
Summary
browse-mcp has an arbitrary file write via unconfined download and state paths
Details

Impact

browser_download wrote a fetched file to join(save_dir, filename) with no validation of save_dir, and browser_save_state / browser_load_state honored an explicit path unchanged. The MCP caller controls these arguments (a malicious MCP client, or an autonomous agent steered by indirect prompt injection on a visited page), so an attacker could supply an arbitrary save_dir (or state path) together with a URL whose response body became the file contents, writing attacker-controlled bytes to any path the process can reach (for example ~/.bashrc, an autostart entry, or a cron file). That is an arbitrary file write that can lead to host code execution. The force_fetch fallback additionally used a raw fetch() that bypassed the BROWSE_MCP_ALLOWED_ORIGINS origin fence.

Estimated severity: CVSS 3.1 around 7.8 (High) for the local / agent-mediated case.

Patches

Fixed in 0.8.2. save_dir is confined under the download root (~/.browse-mcp/downloads) and the explicit state path under ~/.browse-mcp/state; absolute paths and .. escapes are rejected, and download filenames are reduced to a bare basename. force_fetch now also honors the origin fence. Data roots remain relocatable via BROWSE_MCP_HOME. Upgrade to browse-mcp 0.8.2.

Workarounds

Restrict the exposed tools with BROWSE_MCP_TOOLS to a set that excludes browser_download, browser_save_state, and browser_load_state (for example the hardened recipe in SECURITY.md). Note that the allowlist hides the tools from an agent but does not stop a malicious MCP client from calling them by name, so upgrading is the real fix.

  • Reported privately by novice-22.
Severity
8.6 (High)
CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
Show details on source website
To clipboard 

{
  "affected": [
    {
      "database_specific": {
        "last_known_affected_version_range": "\u003c= 0.8.1"
      },
      "package": {
        "ecosystem": "npm",
        "name": "browse-mcp"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "0.8.2"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-55557"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-22"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-08-25T16:28:32Z",
    "nvd_published_at": null,
    "severity": "HIGH"
  },
  "details": "### Impact\n`browser_download` wrote a fetched file to `join(save_dir, filename)` with no validation of `save_dir`, and `browser_save_state` / `browser_load_state` honored an explicit `path` unchanged. The MCP caller controls these arguments (a malicious MCP client, or an autonomous agent steered by indirect prompt injection on a visited page), so an attacker could supply an arbitrary `save_dir` (or state `path`) together with a URL whose response body became the file contents, writing attacker-controlled bytes to any path the process can reach (for example `~/.bashrc`, an autostart entry, or a cron file). That is an arbitrary file write that can lead to host code execution. The `force_fetch` fallback additionally used a raw `fetch()` that bypassed the `BROWSE_MCP_ALLOWED_ORIGINS` origin fence.\n\nEstimated severity: CVSS 3.1 around 7.8 (High) for the local / agent-mediated case.\n\n### Patches\nFixed in 0.8.2. `save_dir` is confined under the download root (`~/.browse-mcp/downloads`) and the explicit state `path` under `~/.browse-mcp/state`; absolute paths and `..` escapes are rejected, and download filenames are reduced to a bare basename. `force_fetch` now also honors the origin fence. Data roots remain relocatable via `BROWSE_MCP_HOME`. Upgrade to browse-mcp 0.8.2.\n\n### Workarounds\nRestrict the exposed tools with `BROWSE_MCP_TOOLS` to a set that excludes `browser_download`, `browser_save_state`, and `browser_load_state` (for example the hardened recipe in SECURITY.md). Note that the allowlist hides the tools from an agent but does not stop a malicious MCP client from calling them by name, so upgrading is the real fix.\n\n- Reported privately by novice-22.",
  "id": "GHSA-m9mq-7m7q-xc6p",
  "modified": "2026-08-25T16:28:32Z",
  "published": "2026-08-25T16:28:32Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/That1Drifter/browse-mcp/security/advisories/GHSA-m9mq-7m7q-xc6p"
    },
    {
      "type": "WEB",
      "url": "https://github.com/That1Drifter/browse-mcp/pull/58"
    },
    {
      "type": "WEB",
      "url": "https://github.com/That1Drifter/browse-mcp/commit/5352a4a56f626254b445bfa07e4bb48c5aad15c1"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/That1Drifter/browse-mcp"
    },
    {
      "type": "WEB",
      "url": "https://github.com/That1Drifter/browse-mcp/blob/v0.8.2/CHANGELOG.md#082---2026-06-13"
    },
    {
      "type": "WEB",
      "url": "https://github.com/That1Drifter/browse-mcp/releases/tag/v0.8.2"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N",
      "type": "CVSS_V4"
    }
  ],
  "summary": "browse-mcp has an arbitrary file write via unconfined download and state paths"
}



Log in or create an account to share your comment.




Tags
Taxonomy of the tags.





Forecast uses a logistic model when the trend is rising, or an exponential decay model when the trend is falling. Fitted via linearized least squares.

Sightings

Author Source Type Date Other

Nomenclature

  • Seen: The vulnerability was mentioned, discussed, or observed by the user.
  • Confirmed: The vulnerability has been validated from an analyst's perspective.
  • Published Proof of Concept: A public proof of concept is available for this vulnerability.
  • Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
  • Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
  • Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
  • Not confirmed: The user expressed doubt about the validity of the vulnerability.
  • Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.



Related by attack behaviour

Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.