request-refactor-plan

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill defines a procedural workflow for creating refactor plans that aligns with standard development practices. All actions, such as codebase exploration and GitHub issue creation, are consistent with its stated purpose.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection through its ingestion of user-provided descriptions and repository content. 1. Ingestion points: user interview (SKILL.md, step 1) and codebase exploration (SKILL.md, step 2). 2. Boundary markers: absent. 3. Capability inventory: repository reading and GitHub issue creation. 4. Sanitization: absent. The outcome of the tool is limited to planning documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 01:02 AM
Security Audit — agent-trust-hub — request-refactor-plan