requesting-code-review
Pass
Audited by Gen Agent Trust Hub on Mar 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
git rev-parse,git log, andgit diffto identify commit ranges and extract code changes for analysis. These commands are necessary for the skill's stated purpose. - [PROMPT_INJECTION]: The subagent processes git diffs and requirements files which are external ingestion points. This creates a surface for indirect prompt injection where malicious instructions could be embedded in the code under review or in documentation to manipulate the reviewer's verdict.
- Ingestion points: Git diff output and the file path specified in
{PLAN_OR_REQUIREMENTS}(processed in code-reviewer.md). - Boundary markers: None; the agent is instructed to read the full content without explicit 'ignore embedded instructions' delimiters.
- Capability inventory: Local file system access and git command execution.
- Sanitization: No filtering or sanitization of the analyzed text is implemented.
Audit Metadata