nexus-eu-ai-compliance
Security checks across malware telemetry and agentic risk
Overview
This is a lightweight instruction-only EU AI Act compliance skill with no executable code, install steps, credentials, persistence, or hidden behavior.
Use this as a planning and documentation aid, not legal advice. Before using it on real compliance work, define the permitted systems, repositories, CI/CD access, and documents, use least-privilege credentials if any tools are connected, and have qualified compliance or legal reviewers validate generated outputs.
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.