sports-betting-analyzer
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWNO_CODE
Full Analysis
- [Prompt Injection] (SAFE): No override markers or jailbreak-style instructions were found. The instructions focus on persona-based output formatting and responsible gambling disclaimers.
- [Data Exposure & Exfiltration] (SAFE): The skill does not contain any code to access local files, environment variables, or perform network requests.
- [Unverifiable Dependencies & Remote Code Execution] (SAFE): No package manifests or remote script downloads are present.
- [Indirect Prompt Injection] (INFO): The skill is designed to process external sports data which could theoretically contain malicious instructions. However, because the skill has no 'write' or 'execute' capabilities (it is instruction-only), the risk is limited to the agent's internal reasoning/output rather than system compromise.
Audit Metadata