prompt-to-skill-reconcile
Pass
Audited by Gen Agent Trust Hub on Nov 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from local workspace files including instructions, scripts, and READMEs. While it lacks explicit boundary markers or sanitization for this content, the risk is mitigated by the lack of network capabilities and a workflow that requires manual confirmation of all changes.
- [SAFE]: The skill is a standard development tool for refactoring local file references. It includes safeguards such as 'disable-model-invocation' to prevent autonomous execution and mandates verification of file encoding and line endings to preserve file integrity.
Audit Metadata