Global Think Tank Analyst
Security checks across malware telemetry and agentic risk
Overview
This is an instruction-only policy analysis skill with no code execution, persistence, credential handling, or hidden data movement in the reviewed artifacts.
Install this if you want structured geopolitical and policy-risk analysis. Treat outputs as decision support rather than legal, sanctions, investment, or compliance advice, verify live-source claims when decisions are high impact, and be cautious when using it in repositories whose AGENTS.md or llms.txt files come from untrusted sources.
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
65/65 vendors flagged this skill as clean.