orchestrating-subagents

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill describes a pattern for orchestrating subagents where the output of one subagent is directly interpolated into the prompt of another. This creates an indirect prompt injection surface.
  • Ingestion points: Results from subagent execution via the task() primitive in SKILL.md.
  • Boundary markers: Not mentioned or implemented in the provided code examples.
  • Capability inventory: The orchestration logic uses the task() primitive which can trigger further subagent actions and file modifications.
  • Sanitization: The instructions do not prescribe sanitization or validation of subagent outputs before they are reused in subsequent prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 07:58 PM
Security Audit — agent-trust-hub — orchestrating-subagents