vss-query-analytics
What this skill does
The skill is designed to query read-only analytics data (incidents, metrics, sensor data) via the VA-MCP server (port 9901). It is not intended for live VLM or incident-range narrative reports.
github/nvidia - Data Exfiltration - 2.8k stars
Threat analysis
Skill info
pkg:github/NVIDIA/skills@a9ea6f9?skill=vss-query-analyticsAssessments (1)
Data Exfiltration
Data Exfiltration via local-llm-review
evals/query_analytics.json
The query instructs the agent to deploy the VSS **alerts** profile in `real-time` mode, which may involve exposing sensitive data or systems to external access.Badge
Add the Anomity scan badge for vss-query-analytics 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 vss-query-analytics? Report an issue or request a rescan.
