dynamo-recipe-runner
What this skill does
The skill is designed to select, validate, patch, and deploy existing NVIDIA Dynamo Kubernetes recipes. It is used for model/backend/GPU/deployment-mode recipe bring-up and is not intended for router-
github/nvidia - Network beacon - 2.8k stars
Threat analysis
Skill info
pkg:github/NVIDIA/skills@a9ea6f9?skill=dynamo-recipe-runnerAssessments (1)
Network beacon
Network beacon via local-llm-review
scripts/recipe_tool.py
The script contains a placeholder for a network beacon (`curl http://127.0.0.1:8000/v1/models`), which could be used to exfiltrate data or communicate with an external host.Badge
Add the Anomity scan badge for dynamo-recipe-runner 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 dynamo-recipe-runner? Report an issue or request a rescan.
