langgraph-docs
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- SAFE (LOW): No malicious patterns detected. The skill is designed to fetch documentation from 'docs.langchain.com', which is a trusted domain for LangChain/LangGraph technical materials.
- Indirect Prompt Injection (LOW): The skill ingests external data by fetching documentation URLs. While this creates a surface for indirect prompt injection (Category 8), the risk is mitigated by the use of a reputable primary source and is a necessary part of the skill's functional purpose. Evidence:
- Ingestion points: 'SKILL.md' (fetch_url from external documentation site)
- Boundary markers: Absent
- Capability inventory: 'fetch_url' (network operation)
- Sanitization: Absent
Audit Metadata