Consilium
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed multi-model advisory workflow that sends the user's council question to configured AI providers, with no hidden scripts or unrelated behavior found.
Install this if you want multi-model deliberation and understand that each council question is sent to several configured model providers. Avoid including secrets, private business details, or highly sensitive legal, medical, or financial information unless you trust every selected provider and your OpenClaw session-retention settings.
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.