full-review

Pass

Audited by Gen Agent Trust Hub on Nov 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources including pull request diffs, descriptions, and comments, and provides the agent with capabilities to execute validation logic and interact with the repository. While the skill enforces human approval for all outputs, the ingestion of untrusted data into the prompt context creates a vulnerability surface.
  • Ingestion points: Processes pull request discussions, current reviews, and code diffs as described in the Workflow section of SKILL.md.
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions for the data being read into the context.
  • Capability inventory: The skill can trigger code validation/execution via the $proof dependency and publish comments or approve PRs via $leaving-pr-comments.
  • Sanitization: There is no mention of sanitizing or escaping the content retrieved from the pull request before it is processed by the agent or passed to dependent skills.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 4, 2026, 12:42 AM