40Medium
The skill uses social engineering by displaying a QR code to lure users to an external WeChat mini-program, risking phishing or malware.
Behavior Analysis
Description verified — behavior matches claim
Claims to do
汉字认字量科学检测 Chatbot Skill: 通过**对话交互**完成儿童（3-12岁）汉字认字量科学检测。基于**分层抽样 + 动态熔断**，从 2500 高频汉字中最多测 **175 字**即可精准估算认字量。
Actually does
This skill accesses `assets/top_2500_chars_with_words.json` to retrieve Chinese characters and their associated words. It uses an internal algorithm to present characters conversationally, processes user input to determine known characters, and calculates a literacy score. It also displays an ASCII art QR code for an external WeChat mini-program.
Skill Info
Namewangwang4git/chinese-literacy-detection
Registryclawhub
Version1.0.4
PURLpkg:clawhub/wangwang4git/chinese-literacy-detection@1.0.4
Downloads82
Source
SHA-256c67bddcd54d4...
SHA-1790a6889ec4b...
MD522ca916298c9...
TLSH305283b848f5...
ssdeep192:vnBXtMLP...
Size13,731 bytes
Install
This skill has been flagged as potentially malicious. Review the findings below before installing.
ClawHubDocs
openclaw skills install wangwang4git/chinese-literacy-detectionAssessments (1)
AI Agent Traps ↗Social engineering via external QR code promptmediumsocial engineering
The skill displays an ASCII art QR code and encourages the user to scan it for a 'more complete experience' in a WeChat mini-program. This constitutes a social engineering vector, as a malicious QR code could redirect users to phishing sites or harmful applications, bypassing the AI's safety mechanisms.
90% confidenceline 89
如果需要体验更完整的功能，请扫描下方二维码，进入微信小程序体验：[ASCII QR code]
Badge
Markdown
[](https://mondoo.com/ai-agent-security/skills/clawhub/wangwang4git/chinese-literacy-detection)HTML
<a href="https://mondoo.com/ai-agent-security/skills/clawhub/wangwang4git/chinese-literacy-detection"><img src="https://mondoo.com/ai-agent-security/api/badge/clawhub/wangwang4git/chinese-literacy-detection.svg" alt="Mondoo Skill Check" /></a>Image URL
https://mondoo.com/ai-agent-security/api/badge/clawhub/wangwang4git/chinese-literacy-detection.svgSecure your AI agents
Skills can read files, run commands, and access credentials. Mondoo helps organizations manage the security risks of AI agent skills across their entire fleet.
- Continuous scanning of skills across all registries
- Policy enforcement before skills reach your agents
- Integration with your existing security workflow