teamharness-task-delegation
Pass
Audited by Gen Agent Trust Hub on Jun 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines a structured workflow for a leader agent to delegate tasks to workers. All operations, including reading and writing files to the 'shared/tasks/' directory and communicating via Matrix, are consistent with the stated purpose of team coordination.
- [PROMPT_INJECTION]: The skill possesses a potential surface for indirect prompt injection via the worker-result processing workflow.
- Ingestion points: The skill reads worker results, specifically the 'STATUS', 'SUMMARY', and 'DELIVERABLES' fields from 'shared/tasks/{task-id}/result.md' when executing the 'check_task' action.
- Boundary markers: The instructions do not define specific delimiters or "ignore previous instruction" guardrails when evaluating result content.
- Capability inventory: The skill has access to tools for file creation/modification (taskflow), project state management (projectflow), and external messaging (teamharness-communication).
- Sanitization: No explicit sanitization or validation logic is specified for worker-provided text before it is processed by the leader agent.
Audit Metadata