fixing-pr-comments
Pass
Audited by Gen Agent Trust Hub on May 8, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes external data in the form of pull request comments, creating a surface for indirect prompt injection attacks.\n
- Ingestion points: Fetches PR review threads via
gh api graphqlinSKILL.md.\n - Boundary markers: Absent; there are no instructions to treat comment content as untrusted or to use delimiters to separate comments from instructions.\n
- Capability inventory: Has the ability to modify local files, create commits, and push changes to the repository (
git push) inSKILL.md.\n - Sanitization: Absent; the skill does not specify any validation or sanitization of the PR comment content before processing it in the triage or fix steps.
Audit Metadata