code-review-assistant

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: No malicious patterns, hardcoded credentials, or suspicious URLs were identified in the skill documentation or instructions.
  • [NO_CODE]: The skill does not contain any executable code, scripts, or package manager files.
  • [PROMPT_INJECTION]: The instructions establish a standard code review persona without attempting to override system constraints or safety filters.
  • [PROMPT_INJECTION]: Analysis of indirect prompt injection surface: 1. Ingestion points: Input code processed in references/commands/code-review-assistant.md; 2. Boundary markers: Not present; 3. Capability inventory: No command execution or network capabilities; 4. Sanitization: None. The surface is present but non-exploitable due to the absence of tool capabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 01:37 AM