orchestration-prompts

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE] (SAFE): No malicious patterns, prompt injections, or obfuscation were detected. The content is purely instructional documentation and does not contain scripts or commands that execute on the host system.
  • [Indirect Prompt Injection] (LOW): The skill defines a multi-agent orchestration pattern where data flows from reconnaissance agents (Scouts) to implementation agents (Builders). This architecture presents a potential surface for indirect prompt injection if the ingested data is not sanitized.
  • Ingestion points: Scout command templates describe reading codebase areas.
  • Boundary markers: Markdown headers are used to delimit reports, which provides minimal protection against adversarial instructions in ingested files.
  • Capability inventory: The orchestrator template defines tools for creating and commanding sub-agents (create_agent, command_agent).
  • Sanitization: No explicit sanitization or boundary-enforcement instructions are included in the templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:16 PM