dispatch

Pass

Audited by Gen Agent Trust Hub on Oct 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates communication between sub-agents by relaying findings from one wave of workers to the next.
  • Ingestion points: Worker responses are collected via tools like plan settle and findings relayed as observations.
  • Boundary markers: Recommended use of source labels like 'T42 worker reported: ...'.
  • Capability inventory: The skill can spawn sub-agents, modify task ledgers, and manage artifacts.
  • Sanitization: Instructions recommend relaying only facts and labeling the source of information.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 9, 2026, 12:46 PM