zai-orchestrator
Pass
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE] (SAFE): No security issues were detected. The skill consists exclusively of instructions for an AI agent to coordinate other tools.
- [Indirect Prompt Injection] (SAFE): The skill ingests data from external sources via search and file reading, which constitutes an injection surface. However, it lacks high-risk capabilities like arbitrary command execution or network exfiltration. * Ingestion points: Data returned by 'zai-web-search' and 'zread'. * Boundary markers: Not specified in instructions. * Capability inventory: Access to 'zai-vision', 'zai-web-search', and 'zread'. * Sanitization: None described.
Audit Metadata