workflow-start

Pass

Audited by Gen Agent Trust Hub on Apr 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill defines a structured approach to workflow management and task execution within a controlled environment.
  • [PROMPT_INJECTION]: The skill incorporates behavior-guiding instructions. It ingests workflow data from an external hook to create tasks, presenting a surface for indirect prompt injection.\n
  • Ingestion points: workflow catalog (referenced via hooks in SKILL.md)\n
  • Boundary markers: None provided\n
  • Capability inventory: TaskCreate tool\n
  • Sanitization: None specified
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 10, 2026, 07:25 AM
Security Audit — agent-trust-hub — workflow-start