looking-up-docs

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [Indirect Prompt Injection Surface] (SAFE): The skill ingests untrusted data from external sources such as documentation websites, search engines, and Git repositories.
  • Ingestion points: WebFetch, WebSearch, Perplexity, and Context7 tools.
  • Boundary markers: None defined.
  • Capability inventory: File system read (Read, Grep, Glob) and network/disk write (git clone).
  • Sanitization: None. The risk is considered minimal as the primary purpose is data/documentation retrieval for developer reference.
  • [Command Execution] (SAFE): The skill recommends using git clone as a fallback strategy to explore source code locally. This is a standard and legitimate developer action for code analysis and does not involve automated execution of untrusted code.
  • [External Downloads] (SAFE): Network operations are limited to searching and fetching documentation content, which aligns with the stated purpose of the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:29 PM