supervise
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists entirely of natural language instructions for the agent and does not include any scripts or executable code.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external task descriptions and reports from sub-agents, which is an inherent injection surface for AI agents. Ingestion points: [task] argument in SKILL.md and sub-agent report files. Boundary markers: None specified in the instructions. Capability inventory: Dispatches sub-agents and manages state files on disk. Sanitization: No explicit sanitization or validation of sub-agent output is described.
- [SAFE]: The skill implements a coordination pattern for sub-agents, managing task dispatching, report collection, and state tracking without invoking dangerous system commands or network operations directly.
Audit Metadata