raffle-winner-picker
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external sources such as Google Sheets, CSV, and Excel files, which creates a potential surface for indirect prompt injection.\n
- Ingestion points: The skill reads external spreadsheet data via URLs or local file paths as specified in the 'How to Use' section.\n
- Boundary markers: The instructions do not include specific delimiters or 'ignore' instructions for the agent when processing external content.\n
- Capability inventory: The agent reads file content and generates text reports or emails based on that data.\n
- Sanitization: No explicit sanitization or validation of the ingested spreadsheet data is described in the instructions.
Audit Metadata