ClawHub
Back to skill

Security audit

Notebooklm Integration

Security checks for vulnerabilities and agentic risk

Overview

This NotebookLM skill is coherent, but it gives an agent broad Google-account actions without enough safety boundaries for deletion, sharing, Drive access, exports, or unpinned updates.

Install only if you are comfortable with an unofficial NotebookLM library acting through your Google login. Use a low-sensitivity or dedicated Google account where possible, avoid secrets or regulated documents, review and pin the package before installing, and require explicit confirmation before delete, share, Drive import, export, or permission-changing actions.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Rogue AgentSelf-Modification, Session Persistence
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill promotes an unofficial integration with Google NotebookLM but does not explicitly warn that notebook contents, uploaded files, URLs, and query data are transmitted to Google services through a third-party library. This omission can cause users to send sensitive or regulated data off-platform without informed consent, especially because the skill is framed as a general workflow helper rather than a data-sharing boundary.

Missing User Warnings

Medium
Confidence
87% confidence
Finding
The skill advertises notebook deletion as a normal capability without any warning about irreversible removal or the need for confirmation safeguards. In an agentic context, that increases the risk of accidental destructive actions against user data, especially if the agent later operationalizes these commands automatically.

Self-Modification

High
Category
Rogue Agent
Content
## Updating the Skill

To update this skill to the latest version from the GitHub repository, follow these steps:

1. Clone or pull the latest version of the notebooklm-py repository:
   ```bash
Confidence
91% confidence
Finding
The skill includes instructions to update itself by cloning or pulling the latest code from an external GitHub repository and reinstalling it. This is a self-modification/supply-chain risk because it encourages replacing the running skill dependency set with unpinned remote code, potentially introducing malicious or compromised updates without review.

Static analysis

No suspicious patterns detected.