skills/neversight/skills_feed/review/Gen Agent Trust Hub

review

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOWNO_CODE
Full Analysis
  • NO_CODE (SAFE): No executable scripts, logic, or implementation files were provided. The skill contains only textual descriptions in multiple languages, offering no surface for direct code execution or functional exploits.
  • PROMPT_INJECTION (SAFE): The provided metadata text does not contain any patterns associated with prompt injection, safety bypasses, or instructions intended to override agent behavior.
  • INDIRECT_PROMPT_INJECTION (INFO): While the claimed functionality (code review and PR auditing) represents a significant indirect injection surface, no implementation was provided to evaluate sanitization or boundary markers. This observation is restricted to the skill's stated purpose.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 04:38 AM