review
Pass
Audited by Gen Agent Trust Hub on Jun 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to identify repository changes and fetch pull request information.
- Evidence: Use of
git merge-base,git diff, andgh pr viewwithin the workflow and error handling sections. - Context: These commands are restricted to standard version control tools and are necessary for the skill's intended purpose of code review.
- [PROMPT_INJECTION]: The skill ingests untrusted data from git diffs and pull request metadata, creating a surface for indirect prompt injection where malicious content could attempt to influence the agent's summary or verdict.
- Ingestion points: Git diffs processed in Phase 1 and pull request metadata fetched via
gh pr viewin the Error Handling section. - Boundary markers: The skill does not provide explicit delimiters or instructions to the agent to isolate the untrusted code content from its own orchestration logic.
- Capability inventory: The skill uses
gitandghcommand-line tools for read-only operations. - Sanitization: No sanitization, filtering, or validation of the ingested diff content or PR metadata is mentioned.
Audit Metadata