orchestrate-governance-step

Pass

Audited by Gen Agent Trust Hub on May 17, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill dynamically invokes other agent skills based on the output of a diagnostic tool (/plan-next). This behavior is consistent with its stated purpose as an automation executor and is constrained by defined success criteria and human gates for high-impact or sensitive operations.
  • [PROMPT_INJECTION]: The skill processes project documentation (via a diagnostic tool) to determine its next actions. While this technically creates a surface for indirect prompt injection, the risk is mitigated by explicit instructions requiring human confirmation for strategic or creative tasks (Artificial Gates) and strict single-step execution limits.
Audit Metadata
Risk Level
SAFE
Analyzed
May 17, 2026, 04:27 AM
Security Audit — agent-trust-hub — orchestrate-governance-step