EUVD-2026-52819

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...

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...

CVE-2026-59216

Open WebUI prior to 0.10.0 is vulnerable to cross-user code execution via unvalidated Socket.IO event-caller session_id. The get_event_call path delivers execute:python and execute:tool events to a client-supplied session_id after only confirming the session is connected, enabling an attacker who...

GHSA-XCMW-GRXF-WJHJ PraisonAI has unauthenticated RCE via `tool_override.py` (CVE-2026-40287 patch bypass)

TL;DR CVE-2026-40287's fix gated tools.py auto-import behind PRAISONAIALLOWLOCALTOOLS=true in two files toolresolver.py, api/call.py. A third import sink in praisonai/templates/tooloverride.py was missed and remains unguarded. It is reached by the recipe runner on every recipe execution and is...

PraisonAI Vulnerable Untrusted Remote Template Code Execution

PraisonAI treats remotely fetched template files as trusted executable code without integrity verification, origin validation, or user confirmation, enabling supply chain attacks through malicious templates. --- Description When a user installs a template from a remote source e.g., GitHub,...

CVE-2026-32022 OpenClaw < 2026.2.21 - Arbitrary File Read via grep -e Flag Policy Bypass

OpenClaw versions prior to 2026.2.21 contain a stdin-only policy bypass vulnerability in the grep tool within tools.exec.safeBins that allows attackers to read arbitrary files by supplying a pattern via the -e flag parameter. Attackers can include a positional filename operand to bypass file acce...

OpenClaw has an unspecified vulnerability (CNVD-2026-13371)

OpenClaw is an intelligent artificial assistant open-sourced by OpenClaw. OpenClaw suffers from a security vulnerability, which stems from tools.exec.safeBins authentication can be bypassed and can be exploited by an attacker to cause unapproved code execution...