Security audit
Uploadweixin
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed Markdown-to-WeChat formatting workflow with no bundled executable code or hidden data handling, though its referenced helper scripts are missing from the package.
Before installing, note that this package does not include the scripts and references it tells the agent to run. Use it only if those helper files are supplied from a trusted source or you confirm the paths resolve to the intended skill files. Also review the default Upload footer behavior and disable it if you do not want branding added to articles.
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.