orchestrator

Pass

Audited by Gen Agent Trust Hub on Apr 20, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill defines a system for orchestrating multiple parallel agents to process user requests and data, which creates a surface for indirect prompt injection.
  • Ingestion points: User requests and project files enter the agent context and are used to build prompts for subagents and teammates (SKILL.md).
  • Boundary markers: The instructions lack requirements for using delimiters (like XML tags or triple backticks) to separate user data from instructions in generated prompts.
  • Capability inventory: The orchestration logic employs powerful tools including TaskCreate and TeamCreate, which allow subagents to modify the file system and execute terminal commands (SKILL.md, references/patterns.md).
  • Sanitization: There is no instruction to sanitize, validate, or escape content from external files or user input before it is passed to subordinate agents.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 20, 2026, 03:07 AM