looking-up-docs

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • Indirect Prompt Injection (LOW): The skill retrieves and processes documentation from external sources, which introduces a potential surface for indirect prompt injection if the source documentation is malicious.
  • Ingestion points: Documentation content retrieved via the mcp__context7__get-library-docs tool.
  • Boundary markers: Absent; the skill does not instruct the agent to use delimiters or treat the documentation as untrusted data.
  • Capability inventory: Includes local file system access tools (Read, Grep, Glob).
  • Sanitization: None; the skill assumes the integrity of the external documentation provided by the Context7 service.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:04 PM