legacy-modernizer

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill is designed to analyze and refactor legacy codebases, creating a surface for indirect prompt injection via comments or strings in the analyzed source code.
  • Ingestion points: Source code files processed during the technical audit and refactoring phases.
  • Boundary markers: Absent; the instructions do not provide delimiters or 'ignore' directives to help the agent distinguish between legacy code and malicious instructions.
  • Capability inventory: The skill documentation mentions automated refactoring and file deletion ('Phase 6: Full Cutover'), though no scripts for these actions are provided in this skill package.
  • Sanitization: None; the provided scripts merely log filenames and do not validate or sanitize inputs.
  • [External Downloads] (SAFE): The documentation suggests using standard industry tools like 'putout' and 'jscodeshift' for refactoring, but no automated downloads or installations are performed by the skill itself.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:36 PM