code-reviewer

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to analyze external, untrusted data (source code and pull requests), which presents a surface for indirect prompt injection.
  • Ingestion points: Untrusted content enters the context via the Read, Grep, and Glob tools as defined in SKILL.md.
  • Boundary markers: There are no delimiters or instructions provided to the agent to distinguish between its own rules and instructions embedded in the code being reviewed.
  • Capability inventory: The skill has the capability to read and search files using Read, Grep, and Glob tools.
  • Sanitization: No sanitization or escaping mechanisms are implemented for the ingested data.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 03:35 AM