docs-maintainer

Pass

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from repository documentation which may contain instructions designed to subvert the agent's behavior.
  • Ingestion points: Instructions in SKILL.md direct the agent to analyze "README, guide, reference, runbook, or release-documentation".
  • Boundary markers: The instructions lack delimiters or explicit directives to treat the content of documentation files as data rather than instructions.
  • Capability inventory: The skill encourages active code execution through instructions like "Run documented commands in a safe environment when practical" and "Validate snippets... with repository tools".
  • Sanitization: There are no requirements for sanitizing or escaping content extracted from documentation files before processing or execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 1, 2026, 06:02 PM
Security Audit — agent-trust-hub — docs-maintainer