ezviz-open-multimodal-analysis
What this skill does
AI 多模态分析技能，用于通过萤石设备抓图并调用智能体分析接口进行图像理解分析
github/leoyeai - Data Exfiltration - 2.1k stars
Threat analysis
Skill info
pkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=ezviz-open-multimodal-analysisAssessments (2)
Data Exfiltration
Data Exfiltration via local-llm-review
scripts/multimodal_analysis.py
The script sends captured device images to an external API for analysis, which could potentially exfiltrate sensitive visual data if the API is not properly secured or if the analysis is not fully traLeast Privilege
Least Privilege via local-llm-review
SKILL.md
The skill requires access to environment variables containing Ezviz credentials (appKey, appSecret), which should be carefully managed to ensure least privilege principles are followed.Badge
Add the Anomity scan badge for ezviz-open-multimodal-analysis 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 ezviz-open-multimodal-analysis? Report an issue or request a rescan.
