Eu Ai Act Risk Classification Memo
Security checks across malware telemetry and agentic risk
Overview
This is a markdown-only EU AI Act memo-drafting skill with no executable code, installation hooks, persistence, or hidden data movement.
Installers should treat this as a drafting aid, not legal advice. Use supervising counsel for final classification decisions, avoid entering confidential training data or sensitive personal data, and verify current EU AI Act guidance before relying on the memo.
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.