CVE-2026-61647: CWE-22: Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal') in roomi-fields notebooklm-mcp
NotebookLM MCP is an MCP server and HTTP service for interacting with Google NotebookLM and exporting generated content to local vault directories. Versions 1.6.0 through 2.0.2 contain a path traversal vulnerability in the `POST /batch-to-vault` endpoint, also exposed through the `batch_to_vault` MCP tool beginning in version 1.7.0, because attacker-controlled `vault_dir` and `slug_prefix` values can cause Markdown and JSON files to be written outside the intended vault directory to any location writable by the server process. Version 2.0.3 sanitizes `slug_prefix` and supports vault containment when `NOTEBOOKLM_VAULT_ROOT` is configured; containment is not enabled if that variable is unset. Users unable to upgrade should run the server as a dedicated unprivileged account restricted to the intended vault, keep the HTTP endpoint limited to localhost, and validate `vault_dir` values supplied by LLMs processing untrusted content.
AI Analysis
Technical Summary
NotebookLM MCP is a server and HTTP service for Google NotebookLM content export. Versions 1.6.0 through 2.0.2 contain a path traversal vulnerability (CWE-22) in the POST /batch-to-vault endpoint and the batch_to_vault MCP tool (from 1.7.0). This vulnerability arises because attacker-controlled 'vault_dir' and 'slug_prefix' parameters can cause Markdown and JSON files to be written outside the intended vault directory to any location writable by the server process. Version 2.0.3 mitigates this by sanitizing 'slug_prefix' and enabling vault containment when the environment variable NOTEBOOKLM_VAULT_ROOT is set. If this variable is unset, containment is not enforced. The vulnerability has a CVSS 4.0 score of 7.1 (high severity), with network attack vector, low attack complexity, no privileges required, no user interaction, and high impact on integrity.
Potential Impact
An attacker can exploit this vulnerability to write files outside the designated vault directory, potentially overwriting or creating files in arbitrary locations writable by the server process. This can lead to unauthorized file manipulation and compromise of system integrity. The vulnerability does not require user interaction or elevated privileges, increasing its risk. However, no known exploits are reported in the wild.
Mitigation Recommendations
Version 2.0.3 of notebooklm-mcp provides an official fix by sanitizing the 'slug_prefix' parameter and supporting vault containment when the NOTEBOOKLM_VAULT_ROOT environment variable is configured. Users should upgrade to version 2.0.3 or later to fully mitigate this issue. For users unable to upgrade immediately, it is recommended to run the server under a dedicated unprivileged account restricted to the intended vault directory, limit the HTTP endpoint to localhost access only, and validate 'vault_dir' values supplied by LLMs processing untrusted content. Patch status is confirmed by vendor advisory details.
CVE-2026-61647: CWE-22: Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal') in roomi-fields notebooklm-mcp
Description
NotebookLM MCP is an MCP server and HTTP service for interacting with Google NotebookLM and exporting generated content to local vault directories. Versions 1.6.0 through 2.0.2 contain a path traversal vulnerability in the `POST /batch-to-vault` endpoint, also exposed through the `batch_to_vault` MCP tool beginning in version 1.7.0, because attacker-controlled `vault_dir` and `slug_prefix` values can cause Markdown and JSON files to be written outside the intended vault directory to any location writable by the server process. Version 2.0.3 sanitizes `slug_prefix` and supports vault containment when `NOTEBOOKLM_VAULT_ROOT` is configured; containment is not enabled if that variable is unset. Users unable to upgrade should run the server as a dedicated unprivileged account restricted to the intended vault, keep the HTTP endpoint limited to localhost, and validate `vault_dir` values supplied by LLMs processing untrusted content.
CVSS v4.0
Score 7.1high
Affected software
roomi-fields
notebooklm-mcp
pkg:github/roomi-fields/notebooklm-mcpRun on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
NotebookLM MCP is a server and HTTP service for Google NotebookLM content export. Versions 1.6.0 through 2.0.2 contain a path traversal vulnerability (CWE-22) in the POST /batch-to-vault endpoint and the batch_to_vault MCP tool (from 1.7.0). This vulnerability arises because attacker-controlled 'vault_dir' and 'slug_prefix' parameters can cause Markdown and JSON files to be written outside the intended vault directory to any location writable by the server process. Version 2.0.3 mitigates this by sanitizing 'slug_prefix' and enabling vault containment when the environment variable NOTEBOOKLM_VAULT_ROOT is set. If this variable is unset, containment is not enforced. The vulnerability has a CVSS 4.0 score of 7.1 (high severity), with network attack vector, low attack complexity, no privileges required, no user interaction, and high impact on integrity.
Potential Impact
An attacker can exploit this vulnerability to write files outside the designated vault directory, potentially overwriting or creating files in arbitrary locations writable by the server process. This can lead to unauthorized file manipulation and compromise of system integrity. The vulnerability does not require user interaction or elevated privileges, increasing its risk. However, no known exploits are reported in the wild.
Mitigation Recommendations
Version 2.0.3 of notebooklm-mcp provides an official fix by sanitizing the 'slug_prefix' parameter and supporting vault containment when the NOTEBOOKLM_VAULT_ROOT environment variable is configured. Users should upgrade to version 2.0.3 or later to fully mitigate this issue. For users unable to upgrade immediately, it is recommended to run the server under a dedicated unprivileged account restricted to the intended vault directory, limit the HTTP endpoint to localhost access only, and validate 'vault_dir' values supplied by LLMs processing untrusted content. Patch status is confirmed by vendor advisory details.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- GitHub_M
- Date Reserved
- 2026-07-10T17:38:57.112Z
- Cvss Version
- 4.0
- State
- PUBLISHED
Threat ID: 6ab19ed755bf5e2cf57bdc36
Added to database: 09/21/2026, 21:17:11 UTC
Last enriched: 09/21/2026, 21:31:45 UTC
Last updated: 09/22/2026, 02:10:31 UTC
Views: 10
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
External Links
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.