request-refactor-plan

Pass

Audited by Gen Agent Trust Hub on Aug 1, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill requires the agent to explore the repository and analyze test coverage, which introduces a surface for indirect prompt injection where malicious instructions embedded in the codebase could attempt to influence the agent's output or actions.
  • Ingestion points: The agent reads repository content and test files in Steps 2 and 6 of the SKILL.md instructions.
  • Boundary markers: The instructions do not define specific delimiters or guardrail instructions for the agent to follow when processing external repository data.
  • Capability inventory: The skill has the capability to read local project files and write to an external service by creating GitHub issues.
  • Sanitization: The workflow does not include explicit validation or sanitization of the content ingested from the repository before it is incorporated into the generated refactor plan.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 1, 2026, 08:26 AM
Security Audit — agent-trust-hub — request-refactor-plan