Security audit
thinking-cynefin
Security checks across malware telemetry and agentic risk
Overview
This skill is a small reasoning guide for choosing a problem-solving mode and does not request tool access, persistence, credentials, or data movement.
This appears safe to install as a thinking aid. Users should expect it to shape the agent's response format when ambiguity calls for Cynefin classification, but it does not add operational authority or access sensitive data.
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
63/63 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.