looking-up-docs
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from an external service which creates a surface for indirect prompt injection attacks.
- Ingestion points: Data from external library sources is brought into the agent context via the 'mcp__context7__get-library-docs' tool output in 'SKILL.md'.
- Boundary markers: The skill instructions do not specify any delimiters or safety prompts to isolate external documentation from the agent's core instructions.
- Capability inventory: The skill has permission to use file system tools including 'Read', 'Grep', and 'Glob' as specified in the frontmatter of 'SKILL.md'.
- Sanitization: The skill does not implement validation or filtering of the documentation content retrieved from the remote source.
Audit Metadata