orchestrate

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill identifies a local workflow file as the primary source of instructions. This constitutes an ingestion point for agent behavior configuration.
  • Ingestion points: .agents/workflows/orchestrate.md (local path).
  • Boundary markers: None defined in the skill manifest.
  • Capability inventory: Automated CLI execution and subagent spawning as described in the metadata.
  • Sanitization: Not explicitly defined in this configuration file.
  • [COMMAND_EXECUTION]: The skill is designed to perform command-line operations and process management, specifically spawning subagents through the Gemini CLI.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 03:27 AM
Security Audit — agent-trust-hub — orchestrate