request-refactor-plan
Pass
Audited by Gen Agent Trust Hub on Jul 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides structured instructions for a standard developer workflow with no evidence of malicious intent or hidden code.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing external data without explicit sanitization. * Ingestion points: User input and repository content (SKILL.md, steps 1, 2, 4). * Boundary markers: Absent from instructions and the GitHub issue template. * Capability inventory: GitHub tool usage for issue creation (SKILL.md, step 8). * Sanitization: Not implemented for external data before template interpolation.
Audit Metadata