Security audit
Language
Security checks across malware telemetry and agentic risk
Overview
This is a text-only language-learning skill with normal personalization and privacy considerations, not hidden code or unsafe behavior.
Reasonable to install if you want a personalized language tutor. Avoid putting highly sensitive personal, workplace, account, medical, legal, or identity details into practice examples unless you are comfortable sharing them with the agent for tutoring context.
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.