re0
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and rewrite existing 'artifacts', which constitutes an ingestion surface for untrusted data.
- Ingestion points: The workflow requires reading target and nearby artifacts end-to-end (SKILL.md, Workflow steps 2 and 3).
- Capability inventory: The skill is authorized to perform file modifications and structural rewrites (SKILL.md, Workflow steps 6 and 9).
- Boundary markers: The instructions explicitly mandate human-in-the-loop oversight by requiring the agent to 'surface judgment calls' and 'never auto-resolve an ambiguity' (SKILL.md, Rules).
- Sanitization: The skill enforces technical safety during mutation by requiring unicode-safe editing using
PYTHONUTF8=1(SKILL.md, Rules).
Audit Metadata