nda-triage
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions define a comprehensive and professional workflow for triaging NDAs based on standard legal criteria.
- [SAFE]: No malicious patterns such as prompt injection, data exfiltration, or obfuscation were detected.
- [SAFE]: The skill involves processing external NDA documents (Indirect Prompt Injection surface), but contains no high-risk capabilities such as code execution or network access. Ingestion points: User-provided NDA text in chat context. Boundary markers: Absent. Capability inventory: None. Sanitization: Absent.
- [SAFE]: The skill does not request access to any tools or perform network operations, focusing solely on document analysis within the chat context.
Audit Metadata