Security audit
Activated Thinker
Security checks across malware telemetry and agentic risk
Overview
This is a prompt-only thinking aid that changes an agent’s response style without requesting code execution, private data access, persistence, or data movement.
This appears safe to install as a reasoning-style skill. Expect it to sometimes make the agent slow down, suggest alternatives, or coach instead of immediately completing a task, especially during exploratory or creative work.
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.