Browse / Indirect Prompt Injection / CVE-2026-34451
Claude SDK for TypeScript: Memory Tool Path Validation Allows Sandbox Escape to Sibling Directories
- Class
- Indirect Prompt Injection (filed by a model that read the advisory)
- Technique
- Path traversal and file access
- Also involves
- Tool and Agent Misuse
- Affected
- @anthropic-ai/sdk (npm)
- Gets past
- Path restriction
- CVSS
- CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:C/C:L/I:L/A:N
- EPSS
- 0.4% chance of exploitation in 30 days
How it works, in short
A prompt-injected model supplies a path that shares the memory root's name as a string prefix, so the prefix check lets reads and writes reach a sibling directory. (Our summary, written by a model. The source text is below.)
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!
References
- https://github.com/anthropics/anthropic-sdk-typescript/security/advisories/GHSA-5474-4w2j-mq4c
- https://nvd.nist.gov/vuln/detail/CVE-2026-34451
- https://github.com/anthropics/anthropic-sdk-typescript/commit/0ac69b3438ee9c96b21a7d3c39c07b7cdb6995d9
- https://github.com/anthropics/anthropic-sdk-typescript
- https://github.com/anthropics/anthropic-sdk-typescript/releases/tag/sdk-v0.81.0
Source: GitHub Advisory Database, used under CC BY 4.0.