Security audit
Ai Trading Backtester
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed trading backtesting assistant with no evidence of hidden execution, credential access, persistence, or data exfiltration.
This appears safe to install as a backtesting guidance skill. Users should still treat generated trading code and performance numbers as educational, review any Python before running it, use only intended historical data files, and avoid connecting real brokerage accounts or API keys unless they independently add and audit that functionality.
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.