BIT-MLFLOW-2026-2614 Arbitrary File Read via Prompt Tag Source Validation Bypass in mlflow/mlflow

A vulnerability in the createmodelversion handler of mlflow/server/handlers.py in mlflow/mlflow versions 3.9.0 and earlier allows an unauthenticated remote attacker to read arbitrary files from the server's filesystem. The issue arises when a CreateModelVersion request includes the tag...

Dissecting the Black Box: Circuit-Level Analysis of LLM Vulnerability Detection

Large language models LLMs can detect software vulnerabilities, but how do they actually identify vulnerable code? We address this question using mechanistic interpretability; analyzing the internal computations of a neural network to understand its reasoning process.Using Circuit Tracer on...

Malicious code in @mlspace/model-registry (npm)

Part of a dependency confusion attack campaign targeting the @cloudplatform-single-spa and @mlspace npm scopes. The attacker npm user mr.4nd3r50n published 139 scoped packages at the inflated version 99.99.99, which resolves ahead of any private registry version via npm's default version...

The Surface You Test Is Not the Surface That Breaks

Tool-augmented LLM agents are vulnerable to prompt injection: a third party who controls part of the agent's context can plant instructions that the agent then executes as if they came from the user. Current evaluations report a single attack success rate per model on one channel, the tool output...

PT-2026-44487

vllm-project/vllm version 0.14.1 contains a vulnerability where the trust remote code=True parameter is hardcoded in two model implementation files vllm/model executor/models/nemotron vl.py and vllm/model executor/models/kimi k25.py. This bypasses the user's explicit --trust-remote-code=False...

Honeyval: A Comprehensive Evaluation Framework for LLM-Powered HTTP Honeypots

Honeypots are decoy systems mimicking real system components designed to defend against cyber attacks. Recently, LLMs increasingly serve as simulation backbones for honeypots. They enable defenders to construct high-interaction honeypots with low system security risks. However, LLM-powered honeyp...

Nautobot 代码问题漏洞

Nautobot is a web automation platform developed by the Nautobot team. Versions prior to Nautobot 2.4.33 and 3.1.2 contained code vulnerabilities. These vulnerabilities stemmed from the Webhook data model and related features being configurable by users with sufficient permissions to send requests...

How Reliable Are AI Attackers against a Fixed Vulnerable Target? A 400-Run Empirical Study of LLM Penetration Testing Consistency

Large language models LLMs can autonomously conduct multi-stage cyber attacks, but the consistency of their offensive behavior under repeated trials remains unstudied. This work presents the first large-scale empirical measurement of LLM attack consistency: 400 autonomous penetration testing runs...

vLLM 安全漏洞

vLLM is an open-source LLM-based inference and service engine that features high throughput and efficient memory usage. Version vLLM 0.14.1 contains a security vulnerability caused by the hardcoding of the trustremotecode=True parameter, which may lead to remote code execution...

Automatically Attacking Software Reverse Engineering AI Agents

Software tools for reverse engineering executable binary files, such as Ghidra, enable malware analysts to safely conduct robust static analysis without having access to original source code. Coupled with the analytic power of large language models LLM, agentic systems enabled with tools, such as...

CVE-2026-44710

pamusb provides hardware authentication for Linux using ordinary removable media. Prior to 0.8.7, src/device.c passed the return values of udisksdrivegetserial, udisksdrivegetvendor, and udisksdrivegetmodel directly to strcmp without NULL checks. The GIO/UDisks API documentation states these...

CVE-2026-9372

A flaw has been found in ItzCrazyKns Vane up to 1.12.1. This vulnerability affects unknown code of the file src/app/api/providers/route.ts of the component Model Provider API. This manipulation of the argument baseURL causes server-side request forgery. Remote exploitation of the attack is...

EUVD-2026-32640

LangSmith Client SDKs provide SDK's for interacting with the LangSmith platform. Prior to LangSmith SDK Python 0.8.0 and JS/TS 0.6.0, the LangSmith SDK's prompt pull methods pullprompt / pullpromptcommit in Python, pullPrompt / pullPromptCommit in JS/TS fetch and deserialize prompt manifests from...

CVE-2026-45134

LangSmith Client SDKs provide SDK's for interacting with the LangSmith platform. Prior to LangSmith SDK Python 0.8.0 and JS/TS 0.6.0, the LangSmith SDK's prompt pull methods pullprompt / pullpromptcommit in Python, pullPrompt / pullPromptCommit in JS/TS fetch and deserialize prompt manifests from...

firefox: Mitigation bypass in the DOM: Security component

A flaw was found in Firefox. The Mozilla Foundation's Security Advisory describes the following issue: Mitigation bypass in the DOM: Security component...

firefox: thunderbird: Privilege escalation in the DOM: Workers component

A flaw was found in Firefox and Thunderbird. The Mozilla Foundation's Security Advisory describes the following issue: Privilege escalation in the DOM: Workers component...

firefox: thunderbird: Use-after-free in the DOM: Networking component

A flaw was found in Firefox and Thunderbird. The Mozilla Foundation's Security Advisory describes the following issue: Use-after-free in the DOM: Networking component...

firefox: Mitigation bypass in the DOM: Security component

A flaw was found in Firefox. The Mozilla Foundation's Security Advisory describes the following issue: Mitigation bypass in the DOM: Security component...

firefox: Mitigation bypass in the DOM: Security component

A flaw was found in Firefox. The Mozilla Foundation's Security Advisory describes the following issue: Mitigation bypass in the DOM: Security component...

firefox: thunderbird: Privilege escalation in the DOM: Workers component

A flaw was found in Firefox and Thunderbird. The Mozilla Foundation's Security Advisory describes the following issue: Privilege escalation in the DOM: Workers component...