Security audit
Socratic Dialogue
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only reasoning skill that asks the agent to slow down, clarify assumptions, and check its reasoning without requesting unusual access.
Install it if you want the agent to challenge assumptions and ask clarifying questions during high-stakes or ambiguous work. Avoid enabling it for simple tasks where you want direct, fast answers, because its disclosed behavior intentionally adds friction and questioning.
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
61/61 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.