Security audit
wechat-article-ai-check
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed writing-review helper for WeChat articles and does not show hidden access, persistence, or unsafe behavior.
Before installing, be aware this skill may guide an agent to analyze or rewrite article drafts you provide, and may use web search if you ask it to verify platform rules or compare against online articles. It is designed to avoid unsupported AI-authorship claims and fabricated evidence.
SkillSpector
By NVIDIA
Vulnerability Patterns
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
VirusTotal
64/64 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.