Get a demo — 30 minutes →
Skill scan report

huashu-design

View on GitHub
35 Medium This skill sends sensitive values to an external host. Automated analysis flagged 1 additional risk pattern.

What this skill does

Design automation tool that generates HTML-based prototypes, animations, slideshows, and visualizations using AI. It is designed to be agent-agnostic and works with multiple AI agents like Claude Code

github/alchaincyf - Data Exfiltration - 22.8k stars

ThreatsData Exfiltration Excessive Agency

Threat analysis

Data Exfiltration1 finding
Excessive Agency1 finding

Skill info

Namealchaincyf/huashu-design
Registrygithub
Version1572d43
PURLpkg:github/alchaincyf/huashu-design@1572d43?skill=huashu-design
Stars22.8k

Assessments (2)

Data Exfiltration1 finding HIGH
HIGH

Data Exfiltration via local-llm-review

SECURITY.md

The skill has cloud code that sends compressed video segments to `ark.cn-beijing.volces.com` (Volcengine Ark, ByteDance official API) and TTS text to `openspeech.bytedance.com` (ByteDance official TTS
Excessive Agency1 finding MEDIUM
MEDIUM

Excessive Agency via local-llm-review

LICENSE

The license contains the phrase 'NOT LIMITED TO', which could be interpreted as a signal of excessive agency or broad permissions.

Badge

Add the Anomity scan badge for huashu-design to your README.

Anomity Skill Check badge

Markdown
[![Anomity Skill Check](https://anomity.ai/skills/badge.svg)](https://anomity.ai/skills/github/alchaincyf/huashu-design/)
HTML
<a href="https://anomity.ai/skills/github/alchaincyf/huashu-design/"><img src="https://anomity.ai/skills/badge.svg" alt="Anomity Skill Check"></a>
Image URL
https://anomity.ai/skills/badge.svg

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 huashu-design? Report an issue or request a rescan.

Ask AI about Anomity
ChatGPT Claude Perplexity Google AI Grok