github-pr-review
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes external, untrusted data including pull request diffs and repository source code. This creates a surface for indirect prompt injection where malicious code in a PR could attempt to influence the agent's review logic.
- Ingestion points: The skill fetches data using
gh pr diffand reads surrounding source code from the repository. - Boundary markers: There are no explicit instructions to use delimiters or ignore potential instructions embedded within the diff or source code.
- Capability inventory: The skill can execute shell commands via the
ghCLI and make POST requests to the GitHub API to submit reviews. - Sanitization: The instructions do not specify any sanitization or validation of the fetched diff or code content.
- [COMMAND_EXECUTION]: The skill's workflow involves executing GitHub CLI (
gh) commands and interacting with the GitHub API to fetch PR information and post review comments. These operations are standard and necessary for the skill's primary function.
Audit Metadata