alibaba-wan
What this skill does
AI video and image generation using Alibaba's Wan 2.6 and Wan 2.5 models, via the Atlas Cloud API.
github/leoyeai - Data Exfiltration - 2.1k stars
Threat analysis
Skill info
pkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=alibaba-wanAssessments (2)
Data Exfiltration
Data Exfiltration via local-llm-review
scripts/generate_image.py
The script sends user-generated content (e.g., image prompts, uploaded files) to the Atlas Cloud API at 'https://api.atlascloud.ai/'. While the API is used for legitimate generation tasks, the script Data Exfiltration via local-llm-review
scripts/generate_video.py
The script sends user-generated content (e.g., video prompts, uploaded files) to the Atlas Cloud API at 'https://api.atlascloud.ai/'. Similar to the image generation script, the script does not explicBadge
Add the Anomity scan badge for alibaba-wan 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 alibaba-wan? Report an issue or request a rescan.
