100Critical
The skill is vulnerable to prompt injection, allowing attackers to manipulate its behavior.
Behavior Analysis
Description verified — behavior matches claim
Claims to do
微信公众号接入指南: 让 AI 助手连接微信公众号，自动回复用户消息。
Actually does
This skill provides a guide and `openclaw` commands to integrate an AI assistant with a WeChat Official Account. It instructs the user to manually obtain WeChat AppID/AppSecret and configure a server URL (e.g., `https://your-server.com/wechat`) and Token on the WeChat platform. It then uses `openclaw connect wechat` to input credentials and `openclaw start` to activate the service, allowing for automatic replies, keyword triggers, multi-customer service transfer, and sensitive word filtering configured via `~/.openclaw/config.yaml`. It also provides `openclaw stats wechat` and `openclaw logs` commands.
Skill Info
Nameyang1002378395-cmyk/openclaw-wechat-mp-guide
Registryclawhub
Version1.0.1
PURLpkg:clawhub/yang1002378395-cmyk/openclaw-wechat-mp-guide@1.0.1
Stars1
Downloads1,030
Installs5
Source
SHA-2562b9169fd9767...
SHA-12795e354b67c...
MD54905b61f2775...
TLSH485173294116...
Size2,767 bytes
Install
This skill has been flagged as potentially malicious. Review the findings below before installing.
OpenClawDocs
https://clawhub.ai/yang1002378395-cmyk/openclaw-wechat-mp-guide1,030 downloads5 installs
ClawHubDocs
openclaw skills install yang1002378395-cmyk/openclaw-wechat-mp-guideAssessments (1)
AI Agent Traps ↗Prompt Injection Detectedcriticalprompt injection
DeBERTa classifier detected prompt injection (confidence: 0.99)
99% confidence
Badge
Markdown
[](https://mondoo.com/ai-agent-security/skills/clawhub/yang1002378395-cmyk/openclaw-wechat-mp-guide)HTML
<a href="https://mondoo.com/ai-agent-security/skills/clawhub/yang1002378395-cmyk/openclaw-wechat-mp-guide"><img src="https://mondoo.com/ai-agent-security/api/badge/clawhub/yang1002378395-cmyk/openclaw-wechat-mp-guide.svg" alt="Mondoo Skill Check" /></a>Image URL
https://mondoo.com/ai-agent-security/api/badge/clawhub/yang1002378395-cmyk/openclaw-wechat-mp-guide.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