swarm
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill manages a workflow where multiple sub-agents are spawned to perform tasks, and their results are aggregated into a final report. This creates a surface where malicious content produced or encountered by a sub-agent could influence the parent agent's behavior during the aggregation phase.
- Ingestion points: Results from workers spawned via
delegate_taskare read usingtask_statusin Phase B and processed in Phase C. - Boundary markers: The skill provides strong isolation instructions, stating that 'T3 child agents get only the brief, never the parent's context.'
- Capability inventory: The skill utilizes orchestration tools including
delegate_task,task_status,task_cancel, andt3_thread_launch. - Sanitization: The instructions explicitly include a mitigation step: 'Do not paste raw worker dumps', requiring the agent to consolidate findings rather than echoing them directly into the primary session context.
Audit Metadata