refactor-for-openclaw
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and modify code from an external OpenClaw workspace, which constitutes a surface for indirect prompt injection.
- Ingestion points: Source code files within the OpenClaw workspace as described in SKILL.md.
- Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore embedded commands in the source files.
- Capability inventory: The refactoring process implies that the agent has file read and write capabilities.
- Sanitization: No procedures for escaping or validating ingested code content are included in the instructions.
Audit Metadata