Scanned skills
nvidia/skills rag-eval
Checked the catalogued skill at rag-eval.
D AI-triaged 4
D Security
D; retained sample includes a high finding · SD-007 · what this rule accepts as a false positive →
A Permissions
A set by no findings on this axis
B Transparency
B; retained sample includes a medium finding · SD-007 · what this rule accepts as a false positive →
4 findings
eval/h100.json
eval/h100.json
eval/h100.json
eval/nvidia_hosted.json
1 suppressed by AI triage
eval/nvidia_hosted.json
The file is a README containing documentation; the text merely references DNS exfiltration concepts, not actual malicious activity.