composable-step-design

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • SAFE (SAFE): The skill is primarily documentation and template-based. It defines design patterns for developer workflows but does not execute code or perform network operations.
  • Indirect Prompt Injection (LOW): The proposed workflow architecture involves processing untrusted external data (task descriptions and issue context). While this identifies an attack surface for downstream implementations, the skill itself provides design contracts rather than active code, posing no immediate threat.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:15 PM