Security audit
Agent Architect
Security checks across malware telemetry and agentic risk
Overview
This is a low-risk planning skill that asks architecture questions and uses bundled markdown references without running code or changing the user's system.
Reasonable to install if you want help designing agent systems. Review any recommendations before implementing them, especially around memory, local sync, API integrations, or cloud storage, because those downstream systems can involve private data even though this skill itself does not access or change anything.
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.
Static analysis
No suspicious patterns detected.