skill-refactorer
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external data in the form of other skills, system prompts, and CLAUDE.md files. This creates a potential surface for indirect prompt injection if the files being refactored contain malicious instructions meant to hijack the agent's behavior during the audit process.
- Ingestion points: The skill explicitly instructs the agent to inventory and classify items from 'target skill/prompt' and 'CLAUDE.md' files.
- Boundary markers: The skill does not define specific delimiters or 'ignore' instructions to separate the refactoring logic from the content being analyzed.
- Capability inventory: The skill workflow implies file reading and text transformation capabilities.
- Sanitization: No explicit sanitization, validation, or escaping of the input text is described in the refactoring process.
Audit Metadata