Security audit
风语绘
Security checks across malware telemetry and agentic risk
Overview
The supplied telemetry does not show malicious or high-risk behavior, and the Unicode-control-character signal is not enough by itself to require Review.
This can remain installable, but review the rendered skill text before use and prefer a version with any hidden Unicode/control characters removed for readability and trust.
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
65/65 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.