Security audit
家庭消费意图识别
Security checks across malware telemetry and agentic risk
Overview
This skill is a straightforward household purchase-intent classifier with only minor cautions around its optional web API exposure.
Safe to install for local, user-directed text classification. If using the API server, bind it to localhost or otherwise restrict network access and CORS, and avoid sending sensitive family chat text to a service exposed beyond your machine.
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
66/66 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.