code-reviewer

Pass

Audited by Gen Agent Trust Hub on Aug 2, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted code files and pull request descriptions which could contain adversarial instructions.
  • Ingestion points: Processes external files and PR descriptions via the Read, Grep, and Glob tools as defined in SKILL.md.
  • Boundary markers: The instructions do not define boundary markers or explicit prompts to ignore embedded commands within analyzed code.
  • Capability inventory: Access is limited to reading files (Read, Grep, Glob); no network access or code execution capabilities are enabled.
  • Sanitization: There is no evidence of sanitization or filtering of external content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 2, 2026, 08:52 PM
Security Audit — agent-trust-hub — code-reviewer