loop-orchestrator
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns detected. The skill defines a structured workflow for task orchestration.
- [SAFE]: The workflow incorporates security-positive patterns, specifically the 'Maker/Checker Separation' which requires independent verification of work, and 'Human Checkpoints' for plan approval prior to autonomous execution.
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an ingestion surface by reading state from
docs/LOOP.mdand user-provided task descriptions. While this creates a path for indirect prompt injection if the project files are untrusted, the risk is mitigated by the structured lifecycle and requirement for human approval of the generated plan.
Audit Metadata