Betting
Pass
Audited by Gen Agent Trust Hub on May 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions and architecture focus exclusively on betting math, probability estimation, and risk management. No malicious patterns such as prompt injection, credential harvesting, or unauthorized remote code execution were found.
- [DATA_STORAGE]: The skill stores stateful information (preferences, ticket history, and market notes) in a dedicated local directory (
~/betting/). This behavior is transparently documented in the architecture and setup files. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided market data and live news. While this represents a potential attack surface, the skill lacks the dangerous capabilities (such as shell execution or network requests to arbitrary domains) required to exploit this vector. The risk is considered negligible as the agent's output is restricted to analytical memos.
Audit Metadata