VLM
What this skill does
Implement vision-based AI chat capabilities using the z-ai-web-dev-sdk for image analysis and multimodal interactions.
github/jjyaoao - Third-party dependency usage - 2.7k stars
Threat analysis
Skill info
pkg:github/jjyaoao/HelloAgents@5432566?skill=vlmAssessments (1)
Third-party dependency usage
Third-party dependency usage via local-llm-review
scripts/vlm.ts
The code imports and uses 'z-ai-web-dev-sdk' to interact with a model ('glm-4.6v') and sends image URLs to an external service. This could pose a risk if the SDK is not properly secured or if the modeBadge
Add the Anomity scan badge for VLM 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 VLM? Report an issue or request a rescan.
