request-refactor-plan
Pass
Audited by Gen Agent Trust Hub on Jul 24, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXFILTRATION]: The skill analyzes local repository content and transmits a summarized refactor plan to GitHub by creating an issue. This data flow is intended by the skill design and targets a well-known, trusted service.
- [PROMPT_INJECTION]: The skill is subject to indirect prompt injection because it reads untrusted data from the repository ('Explore the repo', 'Look in the codebase'). Malicious content in the codebase could attempt to influence the agent's logic during the refactoring interview or the content of the generated issue. 1. Ingestion points: Repository files (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: GitHub issue creation (SKILL.md). 4. Sanitization: Absent.
Audit Metadata