Security audit
Expected Value and the Kelly Criterion
Security checks across malware telemetry and agentic risk
Overview
This is a markdown-only educational skill for expected value and Kelly sizing, with no executable behavior or hidden access requests.
This skill is appropriate to install if you want an agent to help reason about repeated bets, investments, ad spend, or similar sizing decisions. Treat its outputs as educational calculations, not professional financial advice, and avoid using it when probabilities or payoffs are speculative or the decision is one-shot.
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.