nda-screening
Pass
Audited by Gen Agent Trust Hub on Apr 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists exclusively of a framework and rules for classifying Non-Disclosure Agreements. It does not perform any system-level operations, network requests, or file manipulations.
- [NO_CODE]: No scripts, binaries, or references to external packages or code execution were found in the skill.
- [SAFE]: The skill involves processing untrusted data (NDA text), which presents a surface for indirect prompt injection. However, because the agent lacks any capabilities or tools (no shell access, no network, no file writes), the impact of such an attack is limited to affecting the accuracy of the generated text response.
- Ingestion points: NDA text provided to the agent for screening.
- Boundary markers: Absent; the skill does not define specific delimiters to separate user data from instructions.
- Capability inventory: None; the skill does not use any tools or commands.
- Sanitization: Absent; no input validation or sanitization logic is described.
Audit Metadata