context7-auto-research
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest external framework and library documentation into the agent's context. This represents an indirect prompt injection attack surface, as an attacker who controls the documentation (or compromises the API source) could embed malicious instructions that the agent might follow.
- Ingestion points: Content is fetched via the Context7 API (SKILL.md).
- Boundary markers: The skill provides no specific delimiters or technical mechanisms to separate the untrusted fetched content from agent instructions, though it warns the user to treat the material as untrusted.
- Capability inventory: While this specific skill focuses on fetching data, it is designed for use within Claude Code, which possesses significant file system and shell execution capabilities.
- Sanitization: No automated sanitization, filtering, or validation of the fetched text is specified.
Audit Metadata