review-pr-changes
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from GitHub Pull Requests, which creates an ingestion point for potential indirect prompt injection attacks.
- Ingestion points: In
SKILL.md, the agent is instructed to fetch the PR body and code changes usinggh pr viewandgh pr diffcommands. - Boundary markers: The instructions lack explicit delimiters or specific guidance to help the agent distinguish between the data being reviewed and potential malicious instructions embedded within that data.
- Capability inventory: The skill utilizes the GitHub CLI (
gh) and thediffstatutility to perform its review tasks. - Sanitization: No sanitization, validation, or filtering of the content retrieved from the PR is performed before the agent processes it.
Audit Metadata