git-pr-watch
Pass
Audited by Gen Agent Trust Hub on Jul 31, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external data from GitHub Pull Request activity (comments, reviews, and CI logs) which could contain instructions intended to manipulate the agent.
- Ingestion points: Data enters the context via
<github-webhook-activity>tags as described inSKILL.md. - Boundary markers: The instructions explicitly label the input as "untrusted external input" and warn the agent not to act on embedded instructions.
- Capability inventory: The skill has access to shell tools (
gh pr view) and delegates to other PR-modifying skills like/git:fix-prand/git:pr-feedback. - Sanitization: The skill mandates using
AskUserQuestionto verify with the user if the input attempts to redirect the task.
Audit Metadata