prediction-market-strategy
Pass
Audited by Gen Agent Trust Hub on Jun 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of strategy documentation and a single utility script (
scripts/sizing.py). All logic is transparent and matches the stated purpose of sizing and backtesting strategies for prediction markets. - [COMMAND_EXECUTION]: There is no command execution or subprocess spawning. The provided Python script is a pure-math utility using only the standard
mathlibrary. - [DATA_EXFILTRATION]: No network access or data exfiltration patterns were detected. The scripts do not perform any HTTP requests or access the local file system for sensitive data.
- [CREDENTIALS_UNSAFE]: No hardcoded API keys, tokens, or credentials were found. The documentation refers to external API tools (e.g.,
kalshi-api) but does not implement them or require secrets here. - [PROMPT_INJECTION]: No prompt injection attempts, instructions to bypass safety guidelines, or role-play markers were detected in the instructions or metadata.
- [EXTERNAL_DOWNLOADS]: The skill does not perform any external downloads or package installations. It relies on the Python standard library.
Audit Metadata