review-code
Pass
Audited by Gen Agent Trust Hub on Mar 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the GitHub CLI (
gh repo view) to determine the default branch and executes repository-defined test suites and linters to verify changes. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection. It processes findings from untrusted sources and has the capability to write to the filesystem and execute code.
- Ingestion points: Code review output from the
/peer-reviewtool and external pull request comments provided during execution (SKILL.md, Step 2). - Boundary markers: No boundary markers or instructions to ignore embedded commands are present to prevent the agent from obeying instructions embedded in the findings.
- Capability inventory: The skill can modify code files (Step 3) and execute arbitrary code via the project's test suite (Step 5).
- Sanitization: There is no evidence of filtering or sanitizing the input data before it is acted upon.
Audit Metadata