NYC

request-refactor-plan

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • SAFE (SAFE): No malicious patterns, obfuscation, or remote execution triggers were detected in the skill instructions. The skill is entirely declarative markdown.
  • Data Exposure (SAFE): The skill follows security best practices by explicitly instructing the agent NOT to include specific file paths or code snippets in the generated GitHub issues, reducing the risk of accidental sensitive information leak during the planning process.
  • Indirect Prompt Injection (LOW): The skill has a surface for indirect prompt injection because it reads codebase content which could be attacker-controlled. However, because the output is a human-readable refactor plan for a GitHub issue rather than a command for automated execution, the severity is minimal. The presence of a structured template and human-in-the-loop interaction provides further mitigation.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:00 PM