Severity by source
CVSS:4.0/AV:L/AC:L/AT:N/PR:L/UI:N/VC:L/VI:L/VA:L/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
Local-only attack requiring low privileges to manipulate outputDir; unchanged scope with low CIA impact consistent with CVSS 4.0 base metrics.
Primary rating from Vendor (VulDB).
CVSS VectorVendor: VulDB
Lifecycle Timeline
3DescriptionCVE.org
A security flaw has been discovered in adolfosalasgomez3011 slidev-builder-mcp 2.1.0. This affects the function generateChart of the file src/tools/generateAssets.ts of the component generateAssets Tool. Performing a manipulation of the argument outputDir results in command injection. The attack is only possible with local access. The project was informed of the problem early through an issue report but has not responded yet.
AnalysisAI
Command injection in slidev-builder-mcp 2.1.0 allows local low-privilege users to execute arbitrary OS commands by passing shell metacharacters in the outputDir argument to the generateChart function of the generateAssets Tool. The attack is confined to local access only (CVSS 4.0 AV:L), and the CVSS 4.0 E:P modifier confirms publicly available proof-of-concept code exists. No vendor patch has been released as the project has not responded to the disclosure; no confirmed active exploitation (not in CISA KEV) has been identified at time of analysis.
Technical ContextAI
The affected component is the generateChart function within src/tools/generateAssets.ts of the adolfosalasgomez3011/slidev-builder-mcp Node.js package version 2.1.0 (CPE: cpe:2.3:a:adolfosalasgomez3011:slidev-builder-mcp:*:*:*:*:*:*:*:*). This package is a Model Context Protocol (MCP) server that wraps Slidev - a markdown-based slide and chart presentation tool - exposing asset generation capabilities as MCP tool calls. CWE-77 (Improper Neutralization of Special Elements used in a Command) identifies the root cause: the outputDir parameter is accepted from the caller and interpolated unsanitized into a shell command within the generateChart function, enabling injection of arbitrary shell metacharacters and operator-controlled OS commands.
RemediationAI
No vendor-released patch has been identified at time of analysis - the project was notified via GitHub issue (https://github.com/adolfosalasgomez3011/slidev-builder-mcp/issues/1) but has not responded. As an immediate compensating control, restrict local system access to the slidev-builder-mcp process to only fully trusted users and processes, since the attack requires local low-privilege access (PR:L). Organizations running this MCP server in automated pipelines should sanitize or reject any outputDir argument containing shell metacharacters (;, |, &, $, ` `, etc.) at the pipeline boundary before the value reaches the generateChart function. Downstream consumers may fork the repository and apply explicit input validation in src/tools/generateAssets.ts to strip or escape shell-special characters from outputDir` as a temporary fix. Removing or disabling the generateAssets Tool entirely is the highest-confidence workaround if chart generation is non-essential, with the trade-off of losing that functionality.
Same weakness CWE-77 – Command Injection
View allSame technique Command Injection
View allShare
External POC / Exploit Code
Leaving vuln.today
EUVD-2026-54780
GHSA-wgq9-x672-9734