Security audit
Link
Security checks across malware telemetry and agentic risk
Overview
This skill is a short documentation-only artifact about inter-agent linking and does not include code, install scripts, credentials, or executable instructions.
This version appears safe to install as conceptual documentation. Treat the networking and synchronization language as descriptive; if a future version adds real agent connections, authentication, or state sharing, review what data it can access and which services it can contact.
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.