codanna-codebase-intelligence

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns detected. The skill body consists of documentation for codebase analysis tools.
  • [PROMPT_INJECTION]: The skill is designed to process external codebase data, which introduces a surface for indirect prompt injection. Ingestion points: Source code and documentation accessed via the described tools in SKILL.md. Boundary markers: Absent from the instructions. Capability inventory: The tools are restricted to code exploration and analysis (semantic_search_docs, find_callers, analyze_impact) with no destructive capabilities. Sanitization: Not mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 03:13 AM