Security audit
thinking-steel-manning
Security checks across malware telemetry and agentic risk
Overview
This is a narrow reasoning skill that guides the agent to fairly evaluate opposing arguments and does not request tool, file, network, credential, or persistence access.
Install this if you want the agent to use a structured steel-manning checklist before accepting or rejecting proposals. It appears low risk, but it may make some decision discussions more verbose or formal when invoked.
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.