nda-triage
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill is comprised entirely of markdown text providing guidelines and classification rules for NDA screening. There are no scripts, binaries, or other executable components included.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted text from external NDA documents. While this represents a potential surface for indirect prompt injection, the risk is mitigated by the fact that the skill has no access to sensitive capabilities such as network tools, file system write operations, or shell execution.- [SAFE]: The skill instructions are transparent and consistent with the stated purpose of assisting a legal team with document triage. No malicious patterns, obfuscation, or persistence mechanisms were detected.
Audit Metadata