Security audit
thinking-socratic
Security checks across malware telemetry and agentic risk
Overview
This skill is a small guidance-only prompt for asking clarifying questions and does not add code execution, persistence, credential access, or hidden behavior.
This appears safe to install as a guidance skill. It may cause the agent to ask short clarifying questions before acting on vague requests, but it does not introduce executable tooling or access sensitive data on its own.
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.