nda-triage
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill implements an attack surface for indirect prompt injection by processing and triaging untrusted external document files.
- Ingestion points: The analytical scripts
scripts/nda_screener.pyandscripts/nda_checklist.pyingest the entire content of user-provided NDA text files. - Boundary markers: The skill does not implement explicit boundary markers or instructions to the agent to ignore potentially malicious instructions embedded within the NDA content.
- Capability inventory: The triage tools are limited to local file system read operations and analysis. No network communication, external package dependencies, or dynamic code execution capabilities (eval/exec) were detected.
- Sanitization: The input text is processed directly using regular expression matching without prior sanitization or filtering, which could allow adversarial document formatting to manipulate the screening results.
Audit Metadata