code-reviewer

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (LOW): The skill is designed to ingest and analyze untrusted data (code for review), which is a primary vector for indirect prompt injection.
  • Ingestion points: Processes external code, pull requests, and configuration files provided by the user (as seen in the 'Capabilities' and 'Example Interactions' sections).
  • Boundary markers: The instructions do not define clear delimiters or instruct the agent to ignore instructions embedded within the code being reviewed.
  • Capability inventory: The skill description claims capabilities for automated analysis and tool integration, though no executable code or subprocess calls are present in this specific file.
  • Sanitization: There are no instructions for the agent to sanitize or escape content found within the code snippets before processing them.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:00 PM