video-understand
What this skill does
Video understanding using the z-ai-web-dev-sdk for analyzing video content, detecting motion, extracting information from frames, and describing scenes.
github/jjyaoao - Third-party SDK Usage - 2.7k stars
Threat analysis
Skill info
pkg:github/jjyaoao/HelloAgents@5432566?skill=video-understandAssessments (1)
Third-party SDK Usage
Third-party SDK Usage via local-llm-review
scripts/video-understand.ts
The code imports and uses the 'z-ai-web-dev-sdk' package to send video URLs to a model ('glm-4.6v') for analysis. This could pose a risk if the SDK is not properly secured or if the model endpoint is Badge
Add the Anomity scan badge for video-understand 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 video-understand? Report an issue or request a rescan.
