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...

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 AI agents have tool access. They can execute shell commands, write files, browse URLs, send emails, and call APIs. Every one of those actions is a potential...

CVE-2026-56838

PraisonAI is a multi-agent teams system. From version 4.5.87 to before version 4.6.59, PraisonAI recipe execution blocks default-denied dangerous tools unless the caller explicitly passes allowdangeroustools=True. The normal recipe.run path enforces this with checktoolpolicy. The streaming path,...

EUVD-2026-108879

PraisonAI is a multi-agent teams system. From version 4.5.87 to before version 4.6.59, PraisonAI recipe execution blocks default-denied dangerous tools unless the caller explicitly passes allowdangeroustools=True. The normal recipe.run path enforces this with checktoolpolicy. The streaming path,...

Pydantic AI Web chat UI (`Agent.to_web()`, `clai web`): a website visited by the developer can trigger agent runs and server-side tool execution on the local chat endpoint

SummaryThe Pydantic AI development web chat UI Agent.toweb, clai web did not check the content type of requests to its chat endpoint. This allowed a website visited by a developer to submit a request to a chat UI running on that developer's machine, causing the served agent to run and to execute...

Pydantic AI Web chat UI (`Agent.to_web()`, `clai web`): a website visited by the developer can trigger agent runs and server-side tool execution on the local chat endpoint

SummaryThe Pydantic AI development web chat UI Agent.toweb, clai web did not check the content type of requests to its chat endpoint. This allowed a website visited by a developer to submit a request to a chat UI running on that developer's machine, causing the served agent to run and to execute...

PYSEC-2026-4287 Pydantic AI Web chat UI (`Agent.to_web()`, `clai web`): a website visited by the developer can trigger agent runs and server-side tool execution on the local chat endpoint

Summary The Pydantic AI development web chat UI Agent.toweb, clai web did not check the content type of requests to its chat endpoint. This allowed a website visited by a developer to submit a request to a chat UI running on that developer's machine, causing the served agent to run and to execute...

PYSEC-2026-4278 Pydantic AI Web chat UI (`Agent.to_web()`, `clai web`): a website visited by the developer can trigger agent runs and server-side tool execution on the local chat endpoint

Summary The Pydantic AI development web chat UI Agent.toweb, clai web did not check the content type of requests to its chat endpoint. This allowed a website visited by a developer to submit a request to a chat UI running on that developer's machine, causing the served agent to run and to execute...

CVE-2026-110841

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...

CVE-2026-54702

Markdown Preview Enhanced is a Markdown preview extension for Visual Studio Code. Prior to 0.8.30, the webview message handler in src/preview-provider.ts accepts an attacker-controlled command value and attacker-controlled args, constructs a command in the crossnote namespace, and invokes...

CVE-2026-110768

Versions of holaOS through 2026.822.1 are vulnerable to an authorization bypass in the channel-gateway Telegram connector . The flaw exists because the connector authorizes senders based on mutable usernames instead of using unique numeric IDs. An attacker can register a released username that is...

CVE-2026-54702: Exposed Dangerous Method or Function

Markdown Preview Enhanced is a Markdown preview extension for Visual Studio Code. Prior to 0.8.30, the webview message handler in src/preview-provider.ts accepts an attacker-controlled command value and attacker-controlled args, constructs a command in the crossnote namespace, and invokes...

PT-2026-114155

Name of the Vulnerable Software and Affected Versions n8n versions prior to 2.41.4 n8n versions prior to 2.42.0 Description An authorization bypass exists in the agent chat resume endpoint. The system accepts a run identifier from the request body without verifying if the suspended checkpoint...

PT-2026-110994

Hi PWN Community, I’m Ariel Fogel, an AI security researcher in the Office of the CTO at Pillar Security. I focus on the places AI systems break once they touch real systems: MCP servers, model repositories, developer machines, credentials, and production infrastructure. One of my most recent...

CVE-2026-107292

A flaw was found in pydantic-ai. The web development chat server fails to validate incoming HTTP Host headers, allowing a remote attacker to achieve unauthorized tool execution and information disclosure. If a developer running the local development server visits a malicious website, an attacker...

CVE-2026-107295

A flaw was found in pydantic-ai-slim. The local development chat interface does not properly validate request content types, allowing a malicious website visited by a developer to send cross-origin requests to the locally hosted server. A remote attacker can exploit this vulnerability to trigger...

CVE-2026-107295

Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 1.34.0 until 1.107.4 and 2.28.0, the Agent.toweb and clai web development chat endpoint has missing request content-type validation. A website visited by a developer can submit a...

CVE-2026-107292

Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 1.34.0 until 2.30.0, the Agent.toweb and clai web development chat server does not validate the Host header, allowing a website visited by a developer to use DNS rebinding to reach a...

Pydantic AI Web chat UI (`Agent.to_web()`, `clai web`): a website visited by the developer can trigger agent runs and server-side tool execution on the local chat endpoint

Summary The Pydantic AI development web chat UI Agent.toweb, clai web did not check the content type of requests to its chat endpoint. This allowed a website visited by a developer to submit a request to a chat UI running on that developer's machine, causing the served agent to run and to execute...

GHSA-H4XC-3QFQ-JF93 Pydantic AI Web chat UI (`Agent.to_web()`, `clai web`): a website visited by the developer can trigger agent runs and server-side tool execution on the local chat endpoint

Summary The Pydantic AI development web chat UI Agent.toweb, clai web did not check the content type of requests to its chat endpoint. This allowed a website visited by a developer to submit a request to a chat UI running on that developer's machine, causing the served agent to run and to execute...