full-pr-review

Pass

Audited by Gen Agent Trust Hub on Nov 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from Pull Requests, including intent descriptions, repository rules, and existing discussion threads. This content could potentially contain instructions aimed at manipulating the agent's review logic.
  • Ingestion points: Pull Request metadata, branch content, and the history of review comments and discussions are fetched into the agent's context.
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' prompts when handling the fetched PR data.
  • Capability inventory: The skill has the capability to analyze code via the $council sub-skill and write data to the remote repository through the $leaving-pr-comments sub-skill.
  • Sanitization: No explicit sanitization or filtering of the external PR content is defined in the workflow.
  • Mitigation: The risk is significantly reduced by a mandatory human-in-the-loop requirement where the user must review and accept every proposed comment individually before publication.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 6, 2026, 09:14 PM