requesting-code-review

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute local git commands (including git rev-parse, git log, and git diff) to retrieve commit hashes and generate diffs for the review process. These operations are restricted to the local repository context.
  • [SAFE]: Analysis of indirect prompt injection surfaces:
  • Ingestion points: Implementation descriptions and project plans are ingested via placeholders (e.g., {DESCRIPTION}, {PLAN_REFERENCE}) in code-reviewer.md.
  • Boundary markers: Absent; the template does not use explicit delimiters to isolate untrusted content.
  • Capability inventory: Shell execution of git commands as defined in SKILL.md and code-reviewer.md.
  • Sanitization: No sanitization or validation of the input fields is performed. This ingestion surface is consistent with the skill's primary purpose and is managed by standard agent instructions provided in the template.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 12:38 PM
Security Audit — agent-trust-hub — requesting-code-review