nda-triage-anthropic
Pass
Audited by Gen Agent Trust Hub on May 16, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill contains logic and checklists for business workflows without any malicious patterns or technical vulnerabilities detected.
- [NO_CODE]: No scripts, dependencies, or executable binaries are included in this skill; it relies entirely on natural language instructions for the agent.
- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it is intended to process external documents (NDAs).
- Ingestion points: Incoming NDA text provided by users for triage.
- Boundary markers: Not explicitly defined in the instructions.
- Capability inventory: No capabilities (file system access, network operations, or shell execution) are used by this skill, nullifying the risk of exploitation.
- Sanitization: Not present as the skill produces text-based analysis only.
Audit Metadata