nnsight-remote-interpretability

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE] (SAFE): The skill is comprised of reference materials and tutorials in Markdown format. No executable scripts, binaries, or malicious instructional patterns were detected.
  • [EXTERNAL_DOWNLOADS] (LOW): The documentation guides users to install the 'nnsight' package via pip and connect to the official NDIF remote execution backend. These are standard operations for the tool's intended use.
  • [CREDENTIALS_UNSAFE] (SAFE): Example code blocks for setting API keys use non-sensitive placeholders such as 'your_key' and 'your_key_here'.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:06 PM