sub-agents
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION] (SAFE): The skill provides instructions for using the Bash tool to create agent configurations and run CLI commands. These are standard operations for the tool's intended purpose of managing a development environment.
- [DATA_EXPOSURE] (SAFE): File system access is documented for standard configuration paths such as .claude/agents/. No access to sensitive credentials, SSH keys, or environment secrets is requested or demonstrated.
- [PROMPT_INJECTION] (SAFE): While the skill describes an architecture where sub-agents ingest instructions from configuration files, it is a static reference. Ingestion points: .claude/agents/ configuration files; Boundary markers: Not specified in examples; Capability inventory: Read, Write, Bash, Edit, Grep, Glob; Sanitization: Relies on the underlying LLM's instruction-following capabilities.
- [SAFE] (SAFE): No obfuscation, persistence mechanisms, or unauthorized network operations were detected in the skill.
Audit Metadata