Security audit
AI副业真假鉴别器
Security checks across malware telemetry and agentic risk
Overview
This skill is a local rule-based checker for AI side-hustle claims and does not show hidden access, persistence, network use, or credential handling.
This appears safe to install as a local heuristic text analyzer. Treat its scam ratings as advisory only, not as financial, legal, or business due diligence.
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
65/65 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.