review-pr
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes command-line tools to interact with the repository and GitHub metadata.
- Executes
gh pr viewto retrieve the base branch name for the pull request. - Executes
git diffto identify changes between the base branch and the current head. - [PROMPT_INJECTION]: The skill functions as a coordinator that ingests external, untrusted data, which presents a surface for indirect prompt injection.
- Ingestion points: Pull request comments are retrieved via a sub-skill in Step 1, and code diffs are retrieved via Git in Step 3.
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in this coordinating skill.
- Capability inventory: The skill has the ability to execute shell commands (
gh,git) and invoke further automation for code modification (/resolve-findings). - Sanitization: No sanitization or validation of the ingested PR content is performed before it is passed to subsequent evaluation skills.
Audit Metadata