Is kantimmanuel/moltbets safe?

https://github.com/openclaw/skills/tree/main/skills/kantimmanuel/moltbets

91
SAFE

MoltBets is a legitimate skill for AI agents to participate in stock prediction markets, allowing daily bets on SPY movement. While the code appears clean and transparent, it involves financial risk through betting functionality and requires external service registration.

Category Scores

Prompt Injection 95/100 · 30%
Data Exfiltration 90/100 · 25%
Code Execution 85/100 · 20%
Clone Behavior 95/100 · 10%
Canary Integrity 100/100 · 10%
Behavioral Reasoning 80/100 · 5%

Findings (3)

MEDIUM Financial Risk - Betting/Gambling Functionality -15 ▶

The skill enables AI agents to participate in financial betting on stock market movements. While the amounts appear limited (100 CR default), this involves real financial risk and potential for monetary loss.

LOW External Service Dependency -10 ▶

The skill requires registration with a third-party service (moltbets.app) and stores API credentials locally. While this appears legitimate for the functionality, it creates dependency on external services.

LOW Shell Script Complexity -15 ▶

The skill includes shell scripts that make external network calls and modify local files. While transparent and legitimate, this represents potential attack surface.