Security audit
brainstorm-council
Security checks across malware telemetry and agentic risk
Overview
This skill is a structured brainstorming prompt that keeps all output in chat and does not request file, network, credential, or persistent access.
Installers should expect this skill to guide the agent through a structured adversarial brainstorming workflow in chat. It may use multiple model calls and ask follow-up questions, but the reviewed artifacts do not ask for access to local data, accounts, tools, or persistent storage.
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
59/59 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.