Security audit
Agent评估设计顾问
Security checks across malware telemetry and agentic risk
Overview
This skill is a narrow advisory checklist for deciding whether a workflow is suitable for an AI agent and does not request sensitive access or perform actions.
This appears safe to install for design-advice use. Treat its output as advisory guidance, especially because it explicitly says it does not replace a full architecture review.
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
64/64 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.