meeting-insights-analyzer

Warn

Audited by Snyk on Feb 16, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.70). The skill explicitly scans and ingests meeting transcripts from a user-specified folder (e.g., .txt/.vtt/.srt/.docx) and instructs users to import/export those transcripts from third-party services (Granola, Zoom, Google Meet, Fireflies.ai, Otter.ai or Google Docs), so the agent will read untrusted, user-generated content provided by external parties as part of its analysis.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 09:50 AM