raffle-winner-picker
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external, untrusted sources which creates a surface for indirect prompt injection attacks.
- Ingestion points: Data is loaded from external Google Sheet URLs and local files like CSV and Excel spreadsheets mentioned in user prompts.
- Boundary markers: The instructions lack explicit delimiters or warnings to isolate external data content from the agent's core instructions.
- Capability inventory: The skill uses the agent's ability to read and parse file contents to perform selection logic.
- Sanitization: No validation or sanitization steps are specified for the data retrieved from external sources.
Audit Metadata