request-refactor-plan
Pass
Audited by Gen Agent Trust Hub on May 13, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by analyzing codebase content and subsequently generating public GitHub issues. Mandatory evidence: 1. Ingestion points: Repository exploration (SKILL.md, Steps 2 and 6); 2. Boundary markers: Absent; 3. Capability inventory: GitHub issue creation (SKILL.md, Step 8); 4. Sanitization: Instruction to exclude file paths and code snippets from the issue description (SKILL.md, Step 8).
- [COMMAND_EXECUTION]: The skill instructions in SKILL.md involve analyzing the repository and creating GitHub issues, which implies the use of system commands or API tools.
Audit Metadata