GHSA-Q5F5-3GJM-7MFM

Vulnerability from github – Published: 2026-04-01 21:15 – Updated: 2026-04-01 21:15
VLAI?
Summary
Claude SDK for Python has Insecure Default File Permissions in Local Filesystem Memory Tool
Details

The local filesystem memory tool in the Anthropic Python SDK created memory files with mode 0o666, leaving them world-readable on systems with a standard umask and world-writable in environments with a permissive umask such as many Docker base images. A local attacker on a shared host could read persisted agent state, and in containerized deployments could modify memory files to influence subsequent model behavior. Both the synchronous and asynchronous memory tool implementations were affected.

Users on the affected versions are advised to update to the latest version.

Claude SDK for Python thanks lucasfutures on HackerOne for the report.

Severity ?
4.8 (Medium)
CVSS:4.0/AV:L/AC:L/AT:N/PR:L/UI:N/VC:L/VI:L/VA:N/SC:N/SI:N/SA:N
Show details on source website
To clipboard 

{
  "affected": [
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "anthropic"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0.86.0"
            },
            {
              "fixed": "0.87.0"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-34450"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-276",
      "CWE-732"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-04-01T21:15:30Z",
    "nvd_published_at": "2026-03-31T22:16:19Z",
    "severity": "MODERATE"
  },
  "details": "The local filesystem memory tool in the Anthropic Python SDK created memory files with mode 0o666, leaving them world-readable on systems with a standard umask and world-writable in environments with a permissive umask such as many Docker base images. A local attacker on a shared host could read persisted agent state, and in containerized deployments could modify memory files to influence subsequent model behavior. Both the synchronous and asynchronous memory tool implementations were affected.\n\nUsers on the affected versions are advised to update to the latest version.\n\nClaude SDK for Python thanks [`lucasfutures`](https://hackerone.com/lucasfutures) on HackerOne for the report.",
  "id": "GHSA-q5f5-3gjm-7mfm",
  "modified": "2026-04-01T21:15:30Z",
  "published": "2026-04-01T21:15:30Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/anthropics/anthropic-sdk-python/security/advisories/GHSA-q5f5-3gjm-7mfm"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-34450"
    },
    {
      "type": "WEB",
      "url": "https://github.com/anthropics/anthropic-sdk-python/commit/715030ceb4d6dd8d3546e999c680e29532bf1255"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/anthropics/anthropic-sdk-python"
    },
    {
      "type": "WEB",
      "url": "https://github.com/anthropics/anthropic-sdk-python/releases/tag/v0.87.0"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:4.0/AV:L/AC:L/AT:N/PR:L/UI:N/VC:L/VI:L/VA:N/SC:N/SI:N/SA:N",
      "type": "CVSS_V4"
    }
  ],
  "summary": "Claude SDK for Python has Insecure Default File Permissions in Local Filesystem Memory Tool"
}


Log in or create an account to share your comment.




Tags
Taxonomy of the tags.




Sightings

Author Source Type Date

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.



Detection rules are retrieved from Rulezet.