granola-transcript

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly retrieves and ingests user-generated meeting transcripts from Granola's MCP endpoint (https://mcp.granola.ai/mcp) via commands like content <meeting_id> and search as described in SKILL.md, and the agent is expected to read/interpret that third-party content to produce summaries, action items, and drive follow-up actions.