PT-2026-25814

🔴 CVE-2025-69902 - Critical A command injection vulnerability in the minimal wrapper.py component of kubectl-mcp-server v1.2.0 allows attackers to execute arbitrary commands via injecting arbitrary shell metacharact... https://t.co/PU0OcLfG2G https://t.co/y3eBStKQr5...

CVE-2025-69902

A command injection vulnerability in the minimalwrapper.py component of kubectl-mcp-server v1.2.0 allows attackers to execute arbitrary commands via injecting arbitrary shell metacharacters...

CVE-2026-4198: Improper Neutralization of Special Elements used in a Command

A vulnerability was determined in hypermodel-labs mcp-server-auto-commit 1.0.0. Affected by this vulnerability is the function getGitChanges of the file index.ts. This manipulation causes command injection. The attack can only be executed locally. The exploit has been publicly disclosed and may b...

CVE-2026-4198

The CVE affects hypermodel-labs/mcp-server-auto-commit 1.0.0. The vulnerability is in the getGitChanges function of index.ts, enabling command injection via a local attack. An exploit has been publicly disclosed. A patch is available (hash: f7d992c830c5f2ec5749852e66c0195e3ed7fe30) and applying i...

CVE-2026-4198 hypermodel-labs mcp-server-auto-commit index.ts getGitChanges command injection

A vulnerability was determined in hypermodel-labs mcp-server-auto-commit 1.0.0. Affected by this vulnerability is the function getGitChanges of the file index.ts. This manipulation causes command injection. The attack can only be executed locally. The exploit has been publicly disclosed and may b...

CVE-2026-4192

A vulnerability has been found in AvinashBole quip-mcp-server 1.0.0. Affected by this vulnerability is the function setupToolHandlers of the file src/index.ts. Such manipulation leads to command injection. The attack may be performed from remote. The exploit has been disclosed to the public and m...

CVE-2026-4192

The CVE-2026-4192 entry concerns AvinashBole quip-mcp-server 1.0.0, where the function setupToolHandlers in src/index.ts is vulnerable to command injection. The vulnerability is described as exploitable remotely, with the exploit publicly disclosed and the project reportedly not responding to the...

CVE-2026-4192 AvinashBole quip-mcp-server index.ts setupToolHandlers command injection

A vulnerability has been found in AvinashBole quip-mcp-server 1.0.0. Affected by this vulnerability is the function setupToolHandlers of the file src/index.ts. Such manipulation leads to command injection. The attack may be performed from remote. The exploit has been disclosed to the public and m...

CVE-2026-4192 AvinashBole quip-mcp-server index.ts setupToolHandlers command injection

A vulnerability has been found in AvinashBole quip-mcp-server 1.0.0. Affected by this vulnerability is the function setupToolHandlers of the file src/index.ts. Such manipulation leads to command injection. The attack may be performed from remote. The exploit has been disclosed to the public and m...

PT-2026-25573

A vulnerability was determined in hypermodel-labs mcp-server-auto-commit 1.0.0. Affected by this vulnerability is the function getGitChanges of the file index.ts. This manipulation causes command injection. The attack can only be executed locally. The exploit has been publicly disclosed and may b...

PT-2026-25567

A vulnerability has been found in AvinashBole quip-mcp-server 1.0.0. Affected by this vulnerability is the function setupToolHandlers of the file src/index.ts. Such manipulation leads to command injection. The attack may be performed from remote. The exploit has been disclosed to the public and m...

CVE-2026-31944

LibreChat is a ChatGPT clone with additional features. From 0.8.2 to 0.8.2-rc3, The MCP Model Context Protocol OAuth callback endpoint accepts the redirect from the identity provider and stores OAuth tokens for the user who initiated the flow, without verifying that the browser hitting the redire...

CVE-2026-31944: Missing Authentication for Critical Function

LibreChat is a ChatGPT clone with additional features. From 0.8.2 to 0.8.2-rc3, The MCP Model Context Protocol OAuth callback endpoint accepts the redirect from the identity provider and stores OAuth tokens for the user who initiated the flow, without verifying that the browser hitting the redire...

CVE-2026-32247

Graphiti is a framework for building and querying temporal context graphs for AI agents. Graphiti versions before 0.28.2 contained a Cypher injection vulnerability in shared search-filter construction for non-Kuzu backends. Attacker-controlled label values supplied through SearchFilters.nodelabel...

CVE-2026-32247

Graphiti is a framework for building and querying temporal context graphs for AI agents. Graphiti versions before 0.28.2 contained a Cypher injection vulnerability in shared search-filter construction for non-Kuzu backends. Attacker-controlled label values supplied through SearchFilters.nodelabel...

CVE-2026-32247 Graphiti vulnerable to Cypher Injection via unsanitized node_labels in search filters

Graphiti is a framework for building and querying temporal context graphs for AI agents. Graphiti versions before 0.28.2 contained a Cypher injection vulnerability in shared search-filter construction for non-Kuzu backends. Attacker-controlled label values supplied through SearchFilters.nodelabel...

Graphiti vulnerable to Cypher Injection via unsanitized node_labels in search filters

Summary Graphiti versions before 0.28.2 contained a Cypher injection vulnerability in shared search-filter construction for non-Kuzu backends. Attacker-controlled label values supplied through SearchFilters.nodelabels were concatenated directly into Cypher label expressions without validation. In...

CVE-2026-31841 Raw exposure of database statements in Hyperterse MCP search tool

Hyperterse is a tool-first MCP framework for building AI-ready backend surfaces from declarative config. Prior to v2.2.0, the search tool allows LLMs to search for tools using natural language. While returning results, Hyperterse also returned the raw SQL queries, exposing statements which were...

EUVD-2026-11385

ha-mcp has XSS via Unescaped HTML in OAuth Consent Form...

Cross-site Scripting (XSS)

Overview ha-mcp is a Home Assistant MCP Server - Complete control of Home Assistant through MCP Affected versions of this package are vulnerable to Cross-site Scripting XSS in the OAuth consent form rendering process. An attacker can execute arbitrary JavaScript in the server operator's browser b...