see-also-docs

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks as it processes untrusted data from external web sources to generate project documentation.
  • Ingestion points: The skill fetches data from web search results, package registries (PyPI, npm, crates.io), and GitHub repository metadata during the discovery phase described in SKILL.md.
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore instructions' warnings when the agent processes the fetched external data.
  • Capability inventory: The skill possesses the capability to perform network operations (web search and fetch) and write to the local file system (creating/updating docs/RELATED_PROJECTS.md).
  • Sanitization: There are no explicit instructions for the agent to sanitize or escape data retrieved from external URLs before interpolating it into the final document.
  • [SAFE]: The skill accesses standard repository manifest files (e.g., pyproject.toml, package.json, Cargo.toml) to identify project names and dependencies, which is expected behavior for its stated purpose and does not involve accessing sensitive user credentials.
  • [SAFE]: External resource discovery is bounded to two search rounds and targets well-known package registries and technology platforms, which are considered reliable sources for mapping software dependencies.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 04:44 PM