qe-pr-review
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data from GitHub PR diffs and descriptions which could contain malicious instructions designed to manipulate the agent's output.
- Ingestion points: SKILL.md uses
gh pr diffandgh pr viewto fetch external content. - Boundary markers: Absent. The skill does not use specific delimiters or instructions to ignore commands within the PR data.
- Capability inventory: SKILL.md uses
gh pr reviewto post content back to GitHub. - Sanitization: Absent. Data from the PR is interpreted directly by the model without filtering.
Audit Metadata