football-betting-analysis

Pass

Audited by Gen Agent Trust Hub on Apr 18, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill makes HTTP GET requests to FlashScore's RapidAPI endpoints and performs web scraping on www.flashscore.co to fetch match previews and statistics. This is the primary purpose of the skill.
  • [COMMAND_EXECUTION]: The skill uses Python scripts (build_match_context.py and generate_teams_csv.py) to process API data. These scripts are invoked with specific match or team IDs and do not execute arbitrary shell commands.
  • [CREDENTIALS_UNSAFE]: The skill requires a RAPIDAPI_KEY. It securely looks for this key in the environment variable RAPIDAPI_KEY or in local configuration files like ~/.claude/settings.json. It does not contain hardcoded secrets.
  • [DATA_EXFILTRATION]: No sensitive local data is accessed or sent to external servers. The network operations are limited to well-known sports data providers.
  • [PROMPT_INJECTION]: The instructions contain strict guidelines to prevent the AI from fabricating data ([N/A] markers) and to use probabilistic language, which serves as a safety constraint against overconfident or false betting advice.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 18, 2026, 02:33 PM