Security audit
pybricks-debug-coach
Security checks across malware telemetry and agentic risk
Overview
This is a text-only coaching skill for Pybricks robot debugging and does not request device control, credentials, persistence, or broad local access.
Before installing, note that this skill is intended to coach debugging from evidence you provide. Do not submit secrets, private files, or identifying information about children. It will not directly connect to or control a LEGO Hub; hardware access would need a separate tool.
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
63/63 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.