GHSA-5474-4W2J-MQ4C

Vulnerability from github – Published: 2026-04-01 21:16 – Updated: 2026-04-24 20:59
VLAI
Summary
Claude SDK for TypeScript: Memory Tool Path Validation Allows Sandbox Escape to Sibling Directories
Details

The local filesystem memory tool in the Anthropic TypeScript SDK validated model-supplied paths using a string prefix check that did not append a trailing path separator. A model steered by prompt injection could supply a crafted path that resolved to a sibling directory sharing the memory root's name as a prefix, allowing reads and writes outside the sandboxed memory directory.

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

Claude SDK for TypeScript thanks hackerone.com/nicksim for reporting this issue!

Show details on source website

{
  "affected": [
    {
      "package": {
        "ecosystem": "npm",
        "name": "@anthropic-ai/sdk"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0.79.0"
            },
            {
              "fixed": "0.81.0"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-34451"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-22",
      "CWE-41"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-04-01T21:16:49Z",
    "nvd_published_at": "2026-03-31T22:16:20Z",
    "severity": "MODERATE"
  },
  "details": "The local filesystem memory tool in the Anthropic TypeScript SDK validated model-supplied paths using a string prefix check that did not append a trailing path separator. A model steered by prompt injection could supply a crafted path that resolved to a sibling directory sharing the memory root\u0027s name as a prefix, allowing reads and writes outside the sandboxed memory directory.\n\nUsers on the affected versions are advised to update to the latest version.\n\nClaude SDK for TypeScript thanks [hackerone.com/nicksim](https://hackerone.com/nicksim) for reporting this issue!",
  "id": "GHSA-5474-4w2j-mq4c",
  "modified": "2026-04-24T20:59:12Z",
  "published": "2026-04-01T21:16:49Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/anthropics/anthropic-sdk-typescript/security/advisories/GHSA-5474-4w2j-mq4c"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-34451"
    },
    {
      "type": "WEB",
      "url": "https://github.com/anthropics/anthropic-sdk-typescript/commit/0ac69b3438ee9c96b21a7d3c39c07b7cdb6995d9"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/anthropics/anthropic-sdk-typescript"
    },
    {
      "type": "WEB",
      "url": "https://github.com/anthropics/anthropic-sdk-typescript/releases/tag/sdk-v0.81.0"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:C/C:L/I:L/A:N",
      "type": "CVSS_V3"
    },
    {
      "score": "CVSS:4.0/AV:N/AC:H/AT:N/PR:N/UI:N/VC:L/VI:L/VA:N/SC:N/SI:N/SA:N",
      "type": "CVSS_V4"
    }
  ],
  "summary": "Claude SDK for TypeScript: Memory Tool Path Validation Allows Sandbox Escape to Sibling Directories"
}



Log in or create an account to share your comment.




Tags
Taxonomy of the tags.


Loading…

Loading…

Loading…

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.

Loading…

Loading…

Loading…

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.


Loading…