google-sheet

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches arbitrary, user-generated Google Sheets content (see SKILL.md "read" command and scripts/sheets.js -> readRange which calls sheets.spreadsheets.values.get), so the agent can ingest external spreadsheet cells that could influence subsequent decisions or tool actions and enable indirect prompt injection.