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...

CVE-2026-110841 n8n before 2.41.4 and 2.42.0 Authorization Bypass in Agent Chat Resume Tool Approval

n8n before 2.41.4 and 2.42.0 contains an authorization bypass in the agent chat resume endpoint, which accepts a run identifier from the request body without verifying that the suspended checkpoint belongs to the caller. Authenticated project members can list and read other members' private agent...

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...

EUVD-2026-43181

PraisonAI: AICoder Arbitrary File Write and Command Execution via LLM Tool Calls...

Sapien: A Stateful Policy Engine for Autonomous AI Agents

Contextual security defenses prevent AI agents from taking rogue actions by synthesizing a task-specific policy and enforcing it on the agent's tool calls. In multi-step tasks, however, which actions are valid often depends on what the agent has already done and learned. We present Sapien, a poli...

ActionGuard: Tool Call Authorization under Poisoned Skills

LLM-based agents extend their capabilities through third-party skills that provide task-specific instructions, scripts, and tool-use procedures. However, malicious instructions inserted into an otherwise benign skill can cause a benign user request to trigger dangerous Tool Calls, including data...

CVE-2026-101084

obot versions before v0.21.1 fail to enforce Access Control Rules on the /mcp-connect endpoint, allowing any authenticated user to connect to restricted MCP servers if they possess the server ID. Attackers can bypass authorization checks to access and manipulate sensitive backend systems through...

CVE-2026-101084: Authorization Bypass Through User-Controlled Key

obot versions before v0.21.1 fail to enforce Access Control Rules on the /mcp-connect endpoint, allowing any authenticated user to connect to restricted MCP servers if they possess the server ID. Attackers can bypass authorization checks to access and manipulate sensitive backend systems through...

EUVD-2026-87147

BerriAI LiteLLM before 1.101.0-rc.1 contains a tenant isolation bypass vulnerability in the semantic cache layer that allows authenticated users to read other tenants' cached responses by exploiting a metadata key mismatch between getsemanticcachetenantscope and getmetadatavariablename. Attackers...

CVE-2026-89032

BerriAI LiteLLM before 1.101.0-rc.1 contains a tenant isolation bypass vulnerability in the semantic cache layer that allows authenticated users to read other tenants' cached responses by exploiting a metadata key mismatch between getsemanticcachetenantscope and getmetadatavariablename. Attackers...

CVE-2026-89032 BerriAI LiteLLM < 1.101.0-rc.1 Tenant Isolation Bypass via Semantic Cache Layer

BerriAI LiteLLM before 1.101.0-rc.1 contains a tenant isolation bypass vulnerability in the semantic cache layer that allows authenticated users to read other tenants' cached responses by exploiting a metadata key mismatch between getsemanticcachetenantscope and getmetadatavariablename. Attackers...

CVE-2026-89032 BerriAI LiteLLM < 1.101.0-rc.1 Tenant Isolation Bypass via Semantic Cache Layer

BerriAI LiteLLM before 1.101.0-rc.1 contains a tenant isolation bypass vulnerability in the semantic cache layer that allows authenticated users to read other tenants' cached responses by exploiting a metadata key mismatch between getsemanticcachetenantscope and getmetadatavariablename. Attackers...

PT-2026-98928

Name of the Vulnerable Software and Affected Versions BerriAI LiteLLM versions prior to 1.101.0-rc.1 Description A tenant isolation bypass exists in the semantic cache layer due to a metadata key mismatch between the get semantic cache tenant scope and get metadata variable name functions...

EUVD-2026-86320

DBHub is a database MCP server for Postgres, MySQL, SQL Server, Oracle, MariaDB, SQLite. Versions prior to 0.22.5 expose an unauthenticated HTTP MCP endpoint when started with the documented HTTP transport mode, for example --transport http --port 8080. The HTTP server attempts to protect...

CVE-2026-82579

Loop with Unreachable Exit Condition Infinite Loop vulnerability in ash-project ashai allows an attacker who can influence a model's output to hang the tool loop and drive unbounded, repeated model requests. AshAi.ToolLoop classifies a model response of :toolcalls, then filters the calls through...

EEF-CVE-2026-82579 AshAi tool loop never terminates when all tool calls are filtered out, enabling denial of service

Summary Loop with Unreachable Exit Condition Infinite Loop vulnerability in ash-project ashai allows an attacker who can influence a model's output to hang the tool loop and drive unbounded, repeated model requests. AshAi.ToolLoop classifies a model response of :toolcalls, then filters the calls...

CVE-2026-82579 AshAi tool loop never terminates when all tool calls are filtered out, enabling denial of service

Loop with Unreachable Exit Condition Infinite Loop vulnerability in ash-project ashai allows an attacker who can influence a model's output to hang the tool loop and drive unbounded, repeated model requests. AshAi.ToolLoop classifies a model response of :toolcalls, then filters the calls through...

CVE-2026-82579

CVE-2026-82579 is an infinite loop vulnerability in the ash_ai Elixir/Erlang library (versions 0.6.0 through before 1.0.0 ), affecting the AshAi.ToolLoop component. When all tool calls are filtered out—either due to a missing valid name or a reused tool_call_id—the loop recurses with a byte-ident...

Beyond the Mandate: A Systematic Security Analysis of the Agent Payments Protocol (AP2)

The Agent Payments Protocol AP2, introduced by Google, enables large language model LLM-driven shopping agents to authorize and execute payments on behalf of users. Its signed Checkout and Payment Mandates protect the integrity of transaction data after signing. Agent interactions and external...

WeClawArena: An Auditable Sandbox and Benchmark for Cross-User Agents Collaboration and Security in Human-Centered Agent Networks

Recent advances in persistent personal-agent frameworks are making human-centered agent networks realistic deployment targets: each user can be served by an AI agent that acts on the user's behalf, maintains state, and communicates with other agents through social and task relations. In these...