raffle-winner-picker
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- Indirect Prompt Injection (LOW): The skill is designed to ingest and process untrusted external data which could contain malicious instructions meant to influence the agent. Ingestion points: External data from Google Sheet URLs, CSV/Excel files, and provided text lists. Boundary markers: No explicit markers or instructions are provided to the agent to ignore instructions hidden within the data. Capability inventory: File reading and remote data access via Google Sheets. Sanitization: No data validation or sanitization steps are mentioned.
- No Code (SAFE): The skill contains only markdown documentation and no executable scripts or configurations, which minimizes the risk of direct command execution or persistence.
Audit Metadata