request-refactor-plan

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the GitHub CLI (gh issue create) to publish the final refactor plan. This command is executed as the final step of the intended workflow and is directed by the data generated during the user interview.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it processes content from the existing codebase and user input.
  • Ingestion points: Codebase content is read via the 'Explore' subagent, and user input is gathered during the interview process (SKILL.md).
  • Boundary markers: No explicit markers or instructions to ignore instructions found within the codebase are provided.
  • Capability inventory: The skill uses gh issue create to perform network-based write operations.
  • Sanitization: There is no explicit sanitization or escaping of the ingested content before it is placed into the GitHub issue template.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 09:06 AM
Security Audit — agent-trust-hub — request-refactor-plan