Security audit
ai-engineer
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only AI engineering helper with no executable code, install scripts, credential requests, or persistence.
This skill is reasonable to install as a general AI engineering prompt helper. As with any AI-generated ML or API integration code, review generated code before running it and provide service credentials only for a separate task you explicitly request.
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
66/66 vendors flagged this skill as clean.