langchain-retrieval
Fail
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions direct the agent to clone a repository from
https://github.com/Eng0AI/langchain-retrieval.git. This downloads third-party code from an external source. - [REMOTE_CODE_EXECUTION]: The commands
pnpm installandpnpm buildare used to install and execute code derived from the repository cloned from the external GitHub repository. - [INDIRECT_PROMPT_INJECTION]:
- Ingestion points: The skill is designed for "Document Q&A with RAG", which processes potentially untrusted external documents as described in
SKILL.md. - Boundary markers: No specific delimiters or instructions are provided to ensure the agent ignores instructions embedded within the retrieved data.
- Capability inventory: The skill environment supports shell command execution and package management (
pnpm). - Sanitization: There is no evidence of sanitization, filtering, or validation for the content retrieved from documents.
Recommendations
- AI detected serious security threats
Audit Metadata