create-plan

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (LOW): The skill processes untrusted project files which could contain malicious instructions.
  • Ingestion points: Files such as README.md, docs/, and other repository documentation.
  • Boundary markers: None present; the skill does not use delimiters or instructions to ignore content within files.
  • Capability inventory: The skill identifies test commands and file paths for future use in a checklist.
  • Sanitization: No content filtering or sanitization is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:14 PM