process-meeting-notes

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests meeting transcripts and summaries from the third‑party Fireflies service via MCP calls (e.g., mcp__fireflies__fireflies_get_transcript and mcp__fireflies__fireflies_get_summary in workflows/process-recent-meeting.md and generate-l10-summary.md) and then reads/interprets that untrusted, user-generated content to extract action items and drive GitHub issue creation, so external content can materially influence agent decisions and tool use.