code-review-pro

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill ingests untrusted user-provided code for review, which is a surface for indirect prompt injection. \n
  • Ingestion points: Code snippets or files provided by users through prompt activation triggers. \n
  • Boundary markers: Absent; there are no instructions to use specific delimiters (like XML tags or specific markdown blocks) to isolate untrusted code from instructions. \n
  • Capability inventory: None; the skill is entirely instructional and does not include any scripts, network operations, or filesystem access. \n
  • Sanitization: Absent; the skill does not instruct the agent to sanitize input or disregard instructions embedded within the analyzed code's comments or metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:38 PM