Security audit
Sparkplug Tap
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed MQTT/Sparkplug data-reading helper with a clearly warned, off-by-default publish path for authorized control changes.
Install only if you intend to connect an agent to MQTT/Sparkplug/UNS brokers. Treat the publish command as operationally sensitive: keep dry runs on unless you have authorization, change control, and confidence that the target topic is safe.
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.