Skip to main content

markdownify-mcp CVE-2026-14702

| EUVDEUVD-2026-41721 LOW
Use of Insufficiently Random Values (CWE-330)
2026-07-05 VulDB GHSA-cf27-pvxx-xmcj
1.1
CVSS 4.0 · Vendor: VulDB

Severity by source

Vendor (VulDB) PRIMARY
1.1 LOW
CVSS:4.0/AV:L/AC:H/AT:N/PR:L/UI:N/VC:L/VI:N/VA:N/SC:N/SI:N/SA:N/E:P/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
vuln.today AI
2.5 LOW

Local-only access with low privileges required; high complexity to time a temp-file race; impact is limited to low confidentiality of converted content with no integrity or availability effect.

3.1 AV:L/AC:H/PR:L/UI:N/S:U/C:L/I:N/A:N
4.0 AV:L/AC:H/AT:N/PR:L/UI:N/VC:L/VI:N/VA:N/SC:N/SI:N/SA:N

Primary rating from Vendor (VulDB).

CVSS VectorVendor: VulDB

Attack Vector
Local
Attack Complexity
High
Privileges Required
Low
User Interaction
None
Scope
X

Lifecycle Timeline

2
CVSS changed
Jul 05, 2026 - 05:22 NVD
2.0 (LOW) 1.1 (LOW)
Analysis Generated
Jul 05, 2026 - 04:52 vuln.today

DescriptionCVE.org

A flaw has been found in zcaceres markdownify-mcp up to 1.1.0. This impacts the function saveToTempFile of the file src/Markdownify.ts of the component webpage-to-markdown/youtube-to-markdown/bing-search-to-markdown. This manipulation causes insufficiently random values. The attack is restricted to local execution. A high degree of complexity is needed for the attack. The exploitability is said to be difficult. The exploit has been published and may be used. The pull request to fix this issue awaits acceptance.

AnalysisAI

Insufficiently random temporary file naming in markdownify-mcp (zcaceres, versions through 1.1.0) exposes transiently written content to local users who can predict or race the generated file path. The saveToTempFile function in src/Markdownify.ts affects the webpage-to-markdown, youtube-to-markdown, and bing-search-to-markdown conversion pipelines, allowing a co-located attacker to read converted content before cleanup. No active exploitation has been confirmed (not in CISA KEV), though a proof-of-concept is publicly available; the overall risk is low given the local-only, high-complexity attack requirements reflected in the CVSS 4.0 score of 2.0.

Technical ContextAI

The vulnerability resides in the saveToTempFile function within src/Markdownify.ts of markdownify-mcp, a Model Context Protocol (MCP) server that converts web, YouTube, and Bing search content into Markdown for use with LLM tool pipelines. CWE-330 (Use of Insufficiently Random Values) identifies the root cause: temporary file names or identifiers are generated with insufficient entropy, making them predictable to other processes or users sharing the same filesystem. This classic insecure temp-file creation pattern - sometimes exploited via symlink attacks or filename brute-forcing - allows a local adversary to read the file contents during the narrow window between creation and deletion. The affected CPE is cpe:2.3:a:zcaceres:markdownify-mcp:*:*:*:*:*:*:*:*, covering all releases up to and including 1.1.0.

RemediationAI

A fix has been proposed in pull request https://github.com/zcaceres/markdownify-mcp/pull/111, but this PR had not yet been merged into a tagged release at the time of analysis - the upstream fix is available but a released patched version is not independently confirmed. Users should monitor that pull request for merge status and upgrade to the patched release once it is published. As an immediate workaround on shared systems, restrict the permissions of the temporary directory used by the tool to mode 0700 so only the owning user can read files within it; the trade-off is that this requires knowledge of and control over the temp path configured or defaulted by the application. Running markdownify-mcp in an isolated user account or unprivileged container effectively eliminates the cross-user read risk with minimal operational impact.

Share

CVE-2026-14702 vulnerability details – vuln.today

This site uses cookies essential for authentication and security. No tracking or analytics cookies are used. Privacy Policy