MQTT
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-style MQTT helper with security guidance and no evidence that it runs code, persists, or accesses private data.
This appears safe to install as an MQTT reference skill. Treat command and broker configuration snippets as examples: use authentication, TLS, ACLs, and careful network binding before applying them to a real broker.
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.
