CVE-2026-1669

Arbitrary file read in the model loading mechanism HDF5 integration in Keras versions 3.0.0 through 3.13.1 on all supported platforms allows a remote attacker to read local files and disclose sensitive information via a crafted .keras model file utilizing HDF5 external dataset references...

CVE-2026-26013

A flaw was found in LangChain. The ChatOpenAI.getnumtokensfrommessages method fetches arbitrary imageurl values without validation when computing token counts for vision-enabled models. This issue allows an attacker to cause Server-Side Request Forgery SSRF by providing malicious image URLs in us...

nmap-mcp

Nmap MCP Server by Vorota AI nmap-mcp is a production-rea...

autopentest-ai

AutoPentest Automated web application penetration testing p...

VulReaD: Knowledge-Graph-Guided Software Vulnerability Reasoning and Detection

Software vulnerability detection SVD is a critical challenge in modern systems. Large language models LLMs offer natural-language explanations alongside predictions, but most work focuses on binary evaluation, and explanations often lack semantic consistency with Common Weakness Enumeration CWE...

Agentic Knowledge Distillation: Autonomous Training of Small Language Models for SMS Threat Detection

SMS-based phishing smishing attacks have surged, yet training effective on-device detectors requires labelled threat data that quickly becomes outdated. To deal with this issue, we present Agentic Knowledge Distillation, which consists of a powerful LLM acts as an autonomous teacher that fine-tun...

Vulnerabilities in Partial TEE-Shielded LLM Inference with Precomputed Noise

The deployment of large language models LLMs on third-party devices requires new ways to protect model intellectual property. While Trusted Execution Environments TEEs offer a promising solution, their performance limits can lead to a critical compromise: using a precomputed, static secret basis ...

Security Assessment of Intel TDX with Support for Live Migration

In the second and third quarters of 2025, Google collaborated with Intel to conduct a security assessment of Intel Trust Domain Extensions TDX, extending Google's previous review and covering major changes since Intel TDX Module 1.0 - namely support for Live Migration and Trusted Domain TD...

CVE-2026-1669: External Control of File Name or Path

Arbitrary file read in the model loading mechanism HDF5 integration in Keras versions 3.0.0 through 3.13.1 on all supported platforms allows a remote attacker to read local files and disclose sensitive information via a crafted .keras model file utilizing HDF5 external dataset references...

PT-2026-7728

Name of the Vulnerable Software and Affected Versions Keras versions 3.0.0 through 3.13.1 Description A flaw exists in the model loading mechanism, specifically within the HDF5 integration of Keras. This issue allows a remote attacker to read local files and potentially disclose sensitive...

Keras security vulnerabilities

Keras is an open-source deep learning framework with multiple backends. Versions of Keras 3.13.1 and earlier contain security vulnerabilities. These vulnerabilities stem from defects in the model loading mechanism HDF5 integration, which could allow remote attackers to read local files through...

Security Threat Modeling for Emerging AI-Agent Protocols: A Comparative Analysis of MCP, A2A, Agora, and ANP

The rapid development of the AI agent communication protocols, including the Model Context Protocol MCP, Agent2Agent A2A, Agora, and Agent Network Protocol ANP, is reshaping how AI agents communicate with tools, services, and each other. While these protocols support scalable multi-agent...

Jailbreaking Leaves a Trace: Understanding and Detecting Jailbreak Attacks from Internal Representations of Large Language Models

Jailbreaking large language models LLMs has emerged as a critical security challenge with the widespread deployment of conversational AI systems. Adversarial users exploit these models through carefully crafted prompts to elicit restricted or unsafe outputs, a phenomenon commonly referred to as...

Arbitrary File Read via Prompt Tag Source Validation Bypass in CreateModelVersion

The createmodelversion handler in mlflow/server/handlers.py uses a client-controlled tag to decide whether to skip source path validation. When a CreateModelVersion request includes the tag mlflow.prompt.isprompt, the helper ispromptrequest returns True, and the entire source validation block...

Measuring AI Security: Separating Signal from Panic

The conversation around AI security is full of anxiety. Every week, new headlines warn of jailbreaks, prompt injection, agents gone rogue, and the rise of LLM-enabled cybercrime. It’s easy to come away with the impression that AI is fundamentally uncontrollable and dangerous, and therefore...

Discord will limit profiles to teen-appropriate mode until you verify your age

Discord announced it will put all existing and new profiles in teen-appropriate mode by default in early March. The teen-appropriate profile mode will remain in place until users prove they are adults. To change a profile to “full access” will require verification by Discord’s age inference model...

de.arbeitsagentur.opdt:keycloak-cassandra-model-tests (>=2.5.6-24.0, <=2.7.4-24.0), org.keycloak:keycloak-guides (24.0.2) +4 more potentially affected by CVE-2025-11537 via org.keycloak:keycloak-quarkus-server (24.0.2)

org.keycloak:keycloak-quarkus-server MAVEN version 24.0.2 is affected by a known vulnerability. The following packages have a transitive dependency on org.keycloak:keycloak-quarkus-server and may be impacted: - de.arbeitsagentur.opdt:keycloak-cassandra-model-tests =2.5.6-24.0, =2.7.4-24.0 -...

MINI-WR2X-PRW2-WR36

Bulletin has no description...

SecCodePRM: A Process Reward Model for Code Security

Large Language Models are rapidly becoming core components of modern software development workflows, yet ensuring code security remains challenging. Existing vulnerability detection pipelines either rely on static analyzers or use LLM/GNN-based detectors trained with coarse program-level...

Protecting Context and Prompts: Deterministic Security for Non-Deterministic AI

Large Language Model LLM applications are vulnerable to prompt injection and context manipulation attacks that traditional security models cannot prevent. We introduce two novel primitives--authenticated prompts and authenticated context--that provide cryptographically verifiable provenance acros...