orchestration
Pass
Audited by Gen Agent Trust Hub on Feb 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious code, credentials, or prompt injection patterns were detected. The skill consists of Markdown-based guidelines for project planning and agent delegation.
- [SAFE]: The orchestration framework emphasizes security and reliability through recursion depth limits, mandatory delegation manifests, and context distillation techniques.
- [SAFE]: The skill addresses architectural surfaces for indirect prompt injection by recommending structured outputs and explicit constraints. Ingestion points: Codebase files and MCP resource discovery. Boundary markers: Use of delegation manifests and context distillation to limit information flow. Capability inventory: Orchestrates tools via MCP servers for filesystem, repository, and database management. Sanitization: Employs JSON-Schema validation for tool arguments and parent-agent validation of subagent outputs.
Audit Metadata