NYC

code-review

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOWPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION] (LOW): Indirect Prompt Injection Surface. The skill is designed to ingest and analyze untrusted external data in the form of code changes and pull request descriptions.
  • Ingestion points: The skill analyzes 'pull requests', 'code changes', and 'modules'.
  • Boundary markers: Absent. The instructions do not include specific delimiters or warnings to ignore instructions that might be embedded within the code comments or documentation being reviewed.
  • Capability inventory: The skill is limited to text-based reasoning and reporting; it does not have autonomous file-write, network, or command execution capabilities defined within its instructions.
  • Sanitization: None. The agent remains susceptible to instructions hidden in the reviewed content (e.g., in-code comments designed to influence the review outcome).
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 05:51 AM