129 matches found
inspector
MCP Inspector A developer tool for inspecting Model Context Protocol MCP servers. It ships as a single package, @modelcontextprotocol/inspector, that provides four ways to inspect a server: Web — a Vite + React + Mantine single-page app with a Node backend. CLI — a scriptable command-line client...
Ajar
Ajar: Measuring Open Privilege in Agent Defenses An agent-security benchmark reports two numbers, attack success and benign utility, and both are read off runs that happened. Neither says what the defense stood ready to allow on the paths no run took. Ajar asks it directly: for each benign task i...
Least-Privilege Auditing of Agent Tool Calls with Intent Graphs and Reasoning-Guided Escalation
LLM agents that call tools are exposed to indirect prompt injection: instructions hidden in tool outputs can steer an agent into calls the user never asked for. We present a runtime audit that derives an executable intent graph from the user's objective and the deployment's tool catalog with one...
CVE-2026-124028
mistral.rs before 0.9.5 contains a delimiter injection vulnerability in mistralrs-core that allows attackers to inject tool calls by placing delimiter strings in text the model quotes. Attackers controlling documents, web pages or tool outputs can embed tags like to make qwen-xml, gemma4 or...
CVE-2026-124028
Versions of mistral.rs before 0.9.5 are affected by a delimiter injection vulnerability in the mistralrs-core component. This flaw occurs because the software fails to properly neutralize delimiter strings within text quoted by the model. An attacker who controls external inputs—such as documents...
EUVD-2026-118436
mistral.rs before 0.9.5 contains a delimiter injection vulnerability in mistralrs-core that allows attackers to inject tool calls by placing delimiter strings in text the model quotes. Attackers controlling documents, web pages or tool outputs can embed tags like to make qwen-xml, gemma4 or...
CVE-2026-62863
MoLing is a computer-use and browser-use based MCP server. Prior to 0.5.0, when MoLing runs in SSE mode using -l, its /sse and /message HTTP endpoints do not authenticate requests and the mcp-go dependency sets Access-Control-Allow-Origin: . A malicious web page can open a cross-origin EventSourc...
CVE-2026-62863
The MoLing MCP server (prior to version 0.5.0 ) is vulnerable to unauthorized tool execution due to unauthenticated SSE and wildcard CORS settings. When running in SSE mode using the -l flag, the /sse and /message endpoints fail to authenticate requests, and the mcp-go dependency sets Access-Cont...
EUVD-2026-114460
MoLing is a computer-use and browser-use based MCP server. Prior to 0.5.0, when MoLing runs in SSE mode using -l, its /sse and /message HTTP endpoints do not authenticate requests and the mcp-go dependency sets Access-Control-Allow-Origin: . A malicious web page can open a cross-origin EventSourc...
CVE-2026-62863 MoLing: unauthenticated SSE and wildcard CORS expose tool sessions
MoLing is a computer-use and browser-use based MCP server. Prior to 0.5.0, when MoLing runs in SSE mode using -l, its /sse and /message HTTP endpoints do not authenticate requests and the mcp-go dependency sets Access-Control-Allow-Origin: . A malicious web page can open a cross-origin EventSourc...
CVE-2026-62863 MoLing: unauthenticated SSE and wildcard CORS expose tool sessions
MoLing is a computer-use and browser-use based MCP server. Prior to 0.5.0, when MoLing runs in SSE mode using -l, its /sse and /message HTTP endpoints do not authenticate requests and the mcp-go dependency sets Access-Control-Allow-Origin: . A malicious web page can open a cross-origin EventSourc...
CVE-2026-62863
MoLing is a computer-use and browser-use based MCP server. Prior to 0.5.0, when MoLing runs in SSE mode using "-l", its "/sse" and "/message" HTTP endpoints do not authenticate requests and the "mcp-go" dependency sets "Access-Control-Allow-Origin: ". A malicious web page can open a cross-origin...
CVE-2026-62863: gojue moling: MoLing is a computer-use and browser-use based MCP server
MoLing is a computer-use and browser-use based MCP server. Prior to 0.5.0, when MoLing runs in SSE mode using -l, its /sse and /message HTTP endpoints do not authenticate requests and the mcp-go dependency sets Access-Control-Allow-Origin: . A malicious web page can open a cross-origin EventSourc...
PT-2026-134207
Name of the Vulnerable Software and Affected Versions MoLing versions prior to 0.5.0 Description When running in SSE mode using the -l flag, the /sse and /message HTTP endpoints do not authenticate requests. Additionally, the mcp-go dependency configures Access-Control-Allow-Origin: , which allow...
Spring AI 2.1 Message Parts: Reasoning That Survives the Round Trip
Spring AI: Message Parts Doc | Upgrade Notes | OpenAI Responses Doc | Session Doc Reasoning models do more than think before they answer. They hand part of that thinking back to you and expect to get it back on the next request. Claude signs its thinking blocks. Gemini attaches thought signatures...
EUVD-2026-111366
The Model Context Protocol Python SDK is the official Python SDK for Model Context Protocol servers and clients. From 1.10.0 until 1.30.0 and 2.2.0, ClientSession, ClientSessionGroup, and Client tool calls validate server-declared outputSchema documents with jsonschema's default resolver, causing...
CVE-2026-116686 Model Context Protocol Python SDK: Client fetched server-chosen $ref URLs while validating tool results against output schemas
The Model Context Protocol Python SDK is the official Python SDK for Model Context Protocol servers and clients. From 1.10.0 until 1.30.0 and 2.2.0, ClientSession, ClientSessionGroup, and Client tool calls validate server-declared outputSchema documents with jsonschema's default resolver, causing...
CVE-2026-116686 Model Context Protocol Python SDK: Client fetched server-chosen $ref URLs while validating tool results against output schemas
The Model Context Protocol Python SDK is the official Python SDK for Model Context Protocol servers and clients. From 1.10.0 until 1.30.0 and 2.2.0, ClientSession, ClientSessionGroup, and Client tool calls validate server-declared outputSchema documents with jsonschema's default resolver, causing...
CVE-2026-58497
Uni-CLI gives people and agents one command interface for websites, browsers, desktop applications, local tools, and MCP. Prior to version 0.225.2, Uni-CLI exposed the legacy JSON-RPC-over-HTTP MCP transport on loopback without validating browser Origin headers before routing requests. A maliciou...
CVE-2026-58497
Uni-CLI gives people and agents one command interface for websites, browsers, desktop applications, local tools, and MCP. Prior to version 0.225.2, Uni-CLI exposed the legacy JSON-RPC-over-HTTP MCP transport on loopback without validating browser Origin headers before routing requests. A maliciou...