nnsight-remote-interpretability

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a legitimate educational resource for the nnsight interpretability framework, providing clear guidance on model tracing and activation manipulation.
  • [EXTERNAL_DOWNLOADS]: The documentation references official project websites (nnsight.net, ndif.us) and a GitHub repository (ndif-team/nnsight). These are standard references for the documented tool.
  • [CREDENTIALS_UNSAFE]: The skill describes how to configure API keys for remote execution using environment variables or configuration objects, correctly employing placeholders like 'your_key' to avoid hardcoding secrets.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 07:53 PM
Security Audit — agent-trust-hub — nnsight-remote-interpretability