raffle-winner-picker
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted participant data from external sources, creating a vulnerability surface where instructions embedded in the data could be interpreted by the agent.
- Ingestion points: The skill instructions in SKILL.md guide the agent to read data from user-provided Google Sheets URLs and local files such as entries.csv and contest-entries.xlsx.
- Boundary markers: No specific delimiters or safety instructions are provided to the agent to distinguish between data and potential commands within the ingested files.
- Capability inventory: The skill utilizes file system and network access capabilities to retrieve the spreadsheet data.
- Sanitization: There is no evidence of input validation or content filtering to prevent the agent from acting on instructions found within the participant lists.
Audit Metadata