w-refactor
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes selected files and repository content to perform refactoring, which constitutes a surface for indirect prompt injection if those files contain malicious instructions.
- Ingestion points: Selected files, repository code, and named concerns are ingested from the workspace (SKILL.md).
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the code are present.
- Capability inventory: The skill instructs the agent to run repository checks, tests, and profilers, and to invoke the
/w-docstool. - Sanitization: No specific sanitization or validation of the ingested code content is described.
Audit Metadata