Security audit
taizi-coding
Security checks across malware telemetry and agentic risk
Overview
This skill stores explicitly confirmed coding preferences locally and uses them to guide future coding help, with no evidence of network access or hidden behavior.
Before installing, understand that the skill may keep a small local memory of coding preferences in ~/coding/ and read it at session start. Only confirm preferences you actually want reused later; you can ask to show or forget stored preferences.
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
59/59 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.