ClawHub

Granola Meeting Notes API

Security checks across malware telemetry and agentic risk

Overview

This is a transparent read-only Granola meeting-notes integration, but it can expose sensitive meeting content through the API key you configure.

Install this only if you want OpenClaw to read your Granola meeting notes and transcripts. Use a least-privilege personal API key when possible, avoid workspace-wide keys unless intended, store the key only in OpenClaw or a secure environment, and be careful when asking for full transcripts or ambiguous meeting lookups.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The trigger text is broad enough to activate on generic meeting-related requests and any mention of 'Granola', which can cause the skill to run in situations where the user did not clearly intend retrieval of meeting records. Because this skill exposes summaries, transcripts, attendee lists, and other workplace metadata, over-invocation increases the chance of unnecessary access to sensitive content.

Missing User Warnings

Medium
Confidence
84% confidence
Finding
The security/data-handling section describes mechanics like read-only access and API-key handling, but it does not clearly warn that the skill may retrieve sensitive meeting summaries, transcripts, attendee identities, and organizational metadata. Without an explicit user-facing sensitivity warning, users may invoke the skill without appreciating the privacy implications of exposing potentially confidential meeting content.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal