CVE-2026-79750

MCPHub is a unified hub for centrally managing and dynamically orchestrating multiple MCP servers/APIs. Prior to version 1.0.30 , while list views and config edits correctly enforce per-user ownership, the tool-execution API does not. Any authenticated non-admin user can invoke tools on MCP serve...

Securekit

Securekit Securekit protects what your models execute—across any AI system. Securekit is a protocol-agnostic security kernel for AI tool execution. It sits between any LLM or agent system and the tools they use, enforcing zero-trust execution, sandbox isolation, and policy-driven control. It is...

EUVD-2026-68308

Generation of Error Message Containing Sensitive Information vulnerability in ash-project ashai discloses internal error text to chat users. In AshAi.ToolLoop and AshAi.Tools, an exception raised while executing a tool was serialized verbatim with Exception.message/1 into the tool-result content...

CVE-2026-82580 AshAi echoes raw tool exception messages into the conversation, disclosing internal details

Generation of Error Message Containing Sensitive Information vulnerability in ash-project ashai discloses internal error text to chat users. In AshAi.ToolLoop and AshAi.Tools, an exception raised while executing a tool was serialized verbatim with Exception.message/1 into the tool-result content...

intentshield

IntentShield Don't filter what your AI says. Filter what it's about to do Pre-execution intent verification for AI agents. Why This Exists...

CVE-2026-55529

PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, the MCP HTTP Stream validateorigin method accepts requestorigin.startswithallowed, so the attacker-controlled localhost.evil.example HTTP origin matches the localhost allowlist. Without an API key, a malicious webpage can submit...

CVE-2026-55529

PraisonAI (a multi-agent teams system) has an origin validation bypass in its MCP HTTP Stream transport. The _validate_origin method uses request_origin.startswith(allowed), so an attacker-controlled origin like http://localhost.evil.example matches the http://localhost allowlist entry via prefix...

PraisonAI has an origin validation bypass in MCP HTTP Stream transport that allows browser-mediated unauthenticated tool execution on local MCP server

Summary PraisonAI's MCP HTTP Stream transport uses an unsafe prefix match when validating the Origin header. The default localhost allowlist includes origins such as http://localhost, and the validation accepts any origin that starts with an allowed value. As a result, an attacker-controlled orig...

CVE-2026-65975

A flaw was found in Pydantic AI's UI adapters, specifically within the sanitizemessages function. This vulnerability allows a remote client to bypass security checks and execute server tools with arguments they provide, rather than those generated by the AI model. This occurs when a trailing clie...

CVE-2026-18830

Insufficient input validation in Amazon Bedrock AgentCore harness might allow an authenticated remote user to execute configured tools bypassing model invocation and security controls via crafted content blocks in conversation messages. AWS has addressed this issue. No customer action is required...

PT-2026-67789

Name of the Vulnerable Software and Affected Versions Amazon Bedrock AgentCore affected versions not specified Description Insufficient input validation in the AgentCore harness may allow an authenticated remote user to execute configured tools. This is achieved by using crafted content blocks in...

CVE-2026-65975

Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. In versions 1.88.0 up to but not including 1.107.1 and 2.0.0b1 up to but not including 2.5.0, the UI adapters AG-UI via Agent.toagui/AGUIAdapter, and Vercel AI via VercelAIAdapter use...

CVE-2026-65975

CVE-2026-65975 affects Pydantic AI AG-UI Adapter (AG-UI via Agent.to_ag_ui()/AGUIAdapter and Vercel AI via VercelAIAdapter) in Pydantic AI versions 1.88.0–1.107.0 and 2.0.0b1–2.4.x. The bug arises because sanitize_messages uses a stripping index computed before sanitization, so when a trailing cl...

CVE-2026-65975 Pydantic AI AG-UI Adapter: A dangling client-submitted tool call can execute when a trailing message is dropped during `sanitize_messages`

Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. In versions 1.88.0 up to but not including 1.107.1 and 2.0.0b1 up to but not including 2.5.0, the UI adapters AG-UI via Agent.toagui/AGUIAdapter, and Vercel AI via VercelAIAdapter use...

Incorrect Authorization

Overview google-adk is an Agent Development Kit Affected versions of this package are vulnerable to Incorrect Authorization via the request confirmation processing in requestconfirmation.py. An attacker can execute unauthorized tools by injecting or manipulating session-history events to forge a...

CVE-2026-18236

A vulnerability in the Agent Development Kit ADK allows for continuation forgery in tool confirmations. An attacker who is able to manipulate or inject events into the session history can execute unauthorized tools by forging a tool confirmation response. This is possible because the framework di...

PT-2026-65861

Name of the Vulnerable Software and Affected Versions Agent Development Kit affected versions not specified Description An issue allows for continuation forgery in tool confirmations. An attacker capable of manipulating or injecting events into the session history can execute unauthorized tools b...

CVE-2026-16204 zevorn rt-claw Telegram-to-AI Tool Execution Flow script.c tool_run_script_execute code injection

A security flaw has been discovered in zevorn rt-claw up to 0.2.0. This affects the function toolrunscriptexecute of the file claw/services/tools/script.c of the component Telegram-to-AI Tool Execution Flow. Performing a manipulation results in code injection. It is possible to initiate the attac...

EUVD-2026-43621

A vulnerability was found in louisho5 picobot up to 0.2.0. This issue affects the function ExecTool.Execute of the file internal/agent/tools/exec.go of the component exec Tool. The manipulation results in os command injection. The attack requires a local approach. The exploit has been made public...

CVE-2026-58500 MCP Appium: Unescaped Locator Data XSS in MCP-UI Resource (createLocatorGeneratorUI)

MCP Appium is an MCP server that provides AI assistants with tools to automate mobile app testing on Android and iOS. In versions prior to 1.85.10, the createLocatorGeneratorUI function interpolates attacker-controlled element attributes — text, content-desc, resource-id, and locator selector...