requesting-code-review

Pass

Audited by Gen Agent Trust Hub on Feb 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local git commands including 'git rev-parse', 'git log', and 'git diff' to identify changes and extract diff content for analysis.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) because it processes untrusted data from the repository without adequate safeguards.
  • Ingestion points: Processes external data from git commit history, diff outputs, and local files referenced in the {PLAN_OR_REQUIREMENTS} placeholder.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the 'code-reviewer.md' template.
  • Capability inventory: Performs subprocess execution via the 'git' CLI.
  • Sanitization: No input validation or sanitization is performed on code diffs or commit messages before they are interpolated into the prompt.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 25, 2026, 08:23 PM