requesting-code-review

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses git commands (git rev-parse, git log, git diff) to identify code changes and perform reviews. These commands are executed locally and are appropriate for the tool's function.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection in code-reviewer.md. 1. Ingestion points: {WHAT_WAS_IMPLEMENTED}, {PLAN_OR_REQUIREMENTS}, and {DESCRIPTION} placeholders in code-reviewer.md. 2. Boundary markers: Absent. 3. Capability inventory: git diff execution within code-reviewer.md. 4. Sanitization: Absent. This is considered safe as the subagent's scope is limited to technical analysis and reporting without high-privilege operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 01:15 AM