Security audit
Agent Betting Stack Advisor
Security checks across malware telemetry and agentic risk
Overview
This is a read-only advisory skill for choosing betting-agent tools, with no code execution or credential access in the artifact.
Before installing, treat this as guidance for a legally and financially sensitive domain: verify local betting and prediction-market rules, use read-only or research-only workflows first, and review any recommended downstream skill or API integration before giving it API keys, wallet access, or trading authority.
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.