Path Traversal in @roomi-fields/notebooklm-mcp (CVE-2026-61647)
Summary
Path traversal in @roomi-fields/notebooklm-mcp (CVE-2026-61647). Risk of unauthorized operations or information disclosure. Exploitable via POST /batch-to-vault. Mitigation: upgrade to 2.0.3 or later.
Original description
The description as published by the source.
Summary
The vault_batch MCP tool (and the equivalent POST /batch-to-vault HTTP endpoint) accepted a caller-supplied vault_dir path that was passed directly to path.resolve() + fs.mkdir() with no containment check. A caller — or a prompt-injected LLM driving the MCP — could therefore create directories and write .md / .json answer files anywhere the server process can write.
The slug_prefix parameter had a parallel, smaller traversal vector: it was concatenated into the filename without sanitization, so a prefix containing / or .. could escape the resolved vault directory through the filename component.
Impact
File write (markdown + JSON sidecars) to any location writable by the server process. The written files are inert content (no code execution by themselves), but in a multi-user context — or when the MCP server is driven by an LLM that has read untrusted content (prompt injection) — this allows an attacker to plant files in sensitive locations (autostart folders, shell startup files, etc.) for downstream exploitation.
The vulnerability exists from v1.6.0 (when the HTTP /batch-to-vault endpoint was introduced) and v1.7.0 (when the same logic was exposed as the batch_to_vault MCP tool) through v2.0.2.
Patch
Fixed in v2.0.3:
- Opt-in containment via
NOTEBOOKLM_VAULT_ROOTenv var. When set,vault_diris resolved relative to that root andrealpath-based containment is enforced. Absolute paths or..segments outsi…
Source: NIST National Vulnerability Database NVD GitHub Advisory
Auto-generated summary
Assembled by SecPulse from the source data (CVSS, CWE, affected versions) using templates — no AI involved. Check the original description and references below for exact details.
A vulnerability tracked as CVE-2026-61647 has been found in @roomi-fields/notebooklm-mcp.
Attackers can target a specific entry point like POST /batch-to-vault over the network to misuse the product.
Risk of unauthorized operations or information disclosure.
What to do: upgrade @roomi-fields/notebooklm-mcp to 2.0.3 or later.
If unsure, ask your IT team or search "@roomi-fields/notebooklm-mcp CVE-2026-61647" on the vendor's site.
CVE-2026-61647 (@roomi-fields/notebooklm-mcp) — CWE-22
Attack surface: POST /batch-to-vault / vault_batch / vault_dir / slug_prefix
Patched: 2.0.3 — apply immediately
Plan: 1) Audit SBOM/dependencies, 2) Stage→prod upgrade, 3) Add WAF/proxy monitoring on affected endpoints, 4) Hunt IOCs in logs.
Refs: see the GHSA / vendor advisory / patched release linked on this page.
Path traversal (CWE-22) exists in @roomi-fields/notebooklm-mcp. Attackers reach the vulnerable code path via POST /batch-to-vault.
Check the vendor advisory for the affected versions of @roomi-fields/notebooklm-mcp. Attack surface: POST /batch-to-vault / vault_batch / vault_dir / slug_prefix.
Severity: ?. Risk of unauthorized operations or information disclosure.
Update to 2.0.3.
Until the patch is applied: disable the affected feature, apply WAF rules, or restrict access via network ACLs.
Search webserver/proxy logs for unusual POST /batch-to-vault requests with malformed payloads or SQL meta-characters. Run grep -r '@roomi-fields/notebooklm-mcp' . against your dependency files (package-lock.json, requirements.txt, go.sum) to find affected services.
Response actions
Concrete steps and command examples for SOC/SRE teams to execute in order
-
1Identify exposure identify
grep -r '@roomi-fields/notebooklm-mcp' . | grep -v node_modulesリポジトリと本番環境の依存ファイル (package-lock.json / requirements.txt / go.sum / Gemfile.lock 等) で
@roomi-fields/notebooklm-mcpを grep し、稼働しているサービス・バージョンを把握する。 -
2Hunt for indicators of compromise detect
grep 'POST /batch-to-vault' /var/log/nginx/access.log | grep -E '(unusual_payload|sqli_pattern)'アクセスログで
POST /batch-to-vaultへの異常なリクエスト (不正な認証ヘッダ・SQLメタ文字)を過去 30〜90日分捜索。WAF/SIEM があれば該当パスのアラート発火履歴を確認。 -
3Apply patch patch
Upgrade @roomi-fields/notebooklm-mcp to 2.0.3ステージング環境で 2.0.3 に上げて回帰テスト → 本番反映。回帰テストはアプリの主要ハッピーパスと、Step 2 で見つけた異常検知の続報チェックを含めること。
-
4Post-deployment verification verify
Replay attack against POST /batch-to-vault on staging to confirm patch closes the vectorパッチ適用後、ステージングで PoC または同等の悪用パターンを再現して脆弱性が閉じたことを確認。本番では Step 2 と同じログクエリでアラート再発が無いか継続監視。
Affected packages
References
- web github.com
- web nvd.nist.gov
- web github.com
- web github.com
- web github.com
- web github.com