extract-my-action-items

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs subagents to call Fireflies MCP APIs (e.g., mcp__fireflies__fireflies_get_transcripts / mcp__fireflies__fireflies_get_transcript in Phase 2) and to read and interpret the returned transcript JSON/lines to extract action items, synthesize notes, and drive Linear ticket creation and Slack DMs, meaning untrusted, user-generated meeting content from Fireflies is ingested and can materially change downstream actions.