task-coordinator
Pass
Audited by Gen Agent Trust Hub on Mar 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill describes patterns for managing multi-step workflows. It uses local configuration via vendor-specific tools and maintains a state ledger in a local file (
.agents/workflow-ledger.yml). No remote network operations, unauthorized file access, or obfuscated code were detected. - [INDIRECT_PROMPT_INJECTION]: The orchestration patterns involve reading workflow state from a local YAML ledger and executing sub-agents via the
Task()tool based on metadata. While this creates an attack surface for data processed at runtime, the risk is inherent to the task orchestration use case and the skill provides appropriate error handling and status management logic. - Ingestion points:
.agents/workflow-ledger.yml,REVIEWER_LIST. - Boundary markers: Not explicitly defined in pattern templates.
- Capability inventory:
Task()sub-agent invocation, file system read/write for ledger maintenance. - Sanitization: Not explicitly implemented in the provided markdown patterns.
Audit Metadata