raffle-winner-picker
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external, untrusted data which presents a surface for indirect prompt injection attacks. * Ingestion points: CSV files, Excel spreadsheets, Google Sheets URLs, and participant lists described in SKILL.md. * Boundary markers: None identified; the instructions do not specify delimiters or safety guardrails for the agent when reading data. * Capability inventory: The skill description implies file system access for local spreadsheets and network access for Google Sheets. * Sanitization: No input validation or filtering of the processed content is specified.
- [EXTERNAL_DOWNLOADS]: The skill documentation identifies external dependencies for data processing. * Evidence: References to 'pandas' and 'gspread' in the Prerequisites section of SKILL.md.
Audit Metadata