granola

Warn

Audited by Snyk on Mar 18, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md shows calls to the public Granola API (https://public-api.granola.ai/v1/notes) that explicitly retrieve meeting transcripts and AI/user-generated summaries (e.g., the "Get a Note with Transcript" / include=transcript flow), meaning the agent ingests untrusted user-generated third-party content that could contain instructions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 18, 2026, 07:17 AM
Issues
1