tao-train-rtdetr
What this skill does
The skill is a legitimate AI/ML training and deployment tool for RT-DETR models, part of the NVIDIA TAO Toolkit. It is used for training, evaluating, distilling, quantizing, exporting, and running inf
github/nvidia - Information Disclosure - 2.8k stars
Threat analysis
Skill info
pkg:github/NVIDIA/skills@a9ea6f9?skill=tao-train-rtdetrAssessments (1)
Information Disclosure
Information Disclosure via local-llm-review
SKILL.md
The skill's metadata includes the author as 'NVIDIA Corporation' and the license as 'Apache-2.0', which is standard and not a risk. However, the skill's documentation does not explicitly mention how iBadge
Add the Anomity scan badge for tao-train-rtdetr to your README.
How Anomity governs this at runtime
Scan-time vetting tells you what a skill says it will do. Anomity's Endpoint Sensor sees what agents actually do: it discovers skills alongside every other AI artifact on the endpoint, and runtime governance can allow, deny, or log the tool calls a skill triggers. Policy violations route to your SIEM, Slack, email, or Jira, backed by a queryable 90-day audit trail.
Book a 30-minute demo to see your own skill inventory.
Methodology and disputes
Every skill is assessed by the Anomity Skill Intelligence engine against its public source; findings indicate risk patterns, not confirmed exploitation. Maintainer of tao-train-rtdetr? Report an issue or request a rescan.
