Security audit
Character Count
Security checks across malware telemetry and agentic risk
Overview
This is a small local character-counting skill with no evidence of hidden access, networking, persistence, or unsafe behavior.
This skill is reasonable to install for plain character-limit checks. Use a platform-specific validator when exact enforcement matters, because some services count URLs, Unicode, or special tokens differently than Python string length.
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
59/59 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.