athanor
Pass
Audited by Gen Agent Trust Hub on May 20, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill is purely instructional and contains no executable code or automated commands that pose a security risk.
- [PROMPT_INJECTION]: The skill is designed to process external codebases as input. While it does not explicitly define boundary markers or sanitization, this is common for refactoring instructions and is managed by the agent's core safety protocols. Ingestion points: SKILL.md 'Inputs' and 'Step 1: Nigredo'. Boundary markers: Absent. Capability inventory: Uses Read, Write, Edit, Bash, Grep, and Glob tools. Sanitization: Absent.
Audit Metadata