docs-review

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes untrusted documentation files and pull request diffs that could contain malicious instructions. \n
  • Ingestion points: Markdown files and git diffs accessed through file reading tools and GitHub MCP tools. \n
  • Boundary markers: The instructions lack explicit delimiters or warnings for the agent to ignore instructions embedded within the documentation content being reviewed. \n
  • Capability inventory: The skill has access to the Bash shell and several GitHub tools capable of creating and submitting pull request reviews. \n
  • Sanitization: There is no evidence of filtering, escaping, or validation of the content ingested from the documentation files.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 04:52 PM
Security Audit — agent-trust-hub — docs-review