improve-doc

Pass

Audited by Gen Agent Trust Hub on May 9, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill loads several sub-skills from the beagle-docs namespace (beagle-docs:docs-style, beagle-docs:tutorial-docs, beagle-docs:howto-docs, beagle-docs:reference-docs, and beagle-docs:explanation-docs), which are resources associated with the author existential-birds.
  • [PROMPT_INJECTION]: The skill processes external markdown content which constitutes an indirect prompt injection surface. Ingestion points: Reads user-provided files at the specified path (SKILL.md). Boundary markers: None explicitly defined to separate instructions from document data. Capability inventory: The skill possesses file-write capabilities, allowing it to update the original document (SKILL.md). Sanitization: Content is not sanitized or escaped prior to processing. Mitigation: The risk is minimized by an interactive refinement loop where the user must review and approve every change before it is applied to the file system.
Audit Metadata
Risk Level
SAFE
Analyzed
May 9, 2026, 12:42 PM