APEX-AGENT: Cognitive Upgrade for AI Agents
Security checks across malware telemetry and agentic risk
Overview
This is a response-style coaching skill that changes how the agent frames answers, with no evidence of code execution, data access, persistence, or hidden setup.
Install this only if you want a broad style and reasoning framework to shape your agent's replies. Because it is intentionally opinionated and applies across tasks, keep task-specific instructions and normal safety requirements above it, especially for medical, legal, financial, security, or compliance work.
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.