Security audit
Clean Text Toolkit
Security checks across malware telemetry and agentic risk
Overview
This skill is a local Python text-processing toolkit with disclosed, user-directed file reads and writes and no evidence of remote calls, persistence, or hidden behavior.
Install only if you want local command-line text utilities. The main practical risk is user error: these scripts process whatever local files you point them at and may write output files, so avoid using sensitive paths unless that is intended.
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.