EUVD-2026-96609

JeecgBoot through 3.9.5 contains a missing authorization vulnerability in the promptExperiment handler of AiragPromptsController that allows any authenticated user to run AI prompt experiments. Low-privileged attackers can supply other users' prompt template and dataset ids to trigger large...

PT-2026-83313

Chainlit through 2.12.0 fails to validate ownership of feedback records in PUT and DELETE endpoints. Authenticated attackers can delete or modify other users' feedback by supplying arbitrary feedback identifiers, corrupting human-rating data used for model evaluation...

ATOBench: Tracing How Autonomous Penetration-Testing Agents Verify Vulnerabilities When Target Evidence Lies

Autonomous penetration-testing agents rely on target responses. These responses guide both subsequent actions and the final report. A deceptive response can therefore redirect both the attack trajectory and the agent's verification process. However, final reports reveal little about how an agent...

A Cybersecurity MLPS Large Language Model with Multi-Path Retrieval Fusion

The Multi-Level Protection Scheme MLPS is a foundational system in China's cybersecurity governance framework. Therefore, accurate analysis and understanding of MLPS requirements are essential. At present, MLPS analysis still relies mainly on manual interpretation of standards and rule-based tool...

A Structured Cyber Threat Intelligence Dataset Using STIX 2.1 Entities and MITRE ATT&CK Mappings

Cyber threat intelligence CTI reports are typically written in unstructured formats, which complicates the extraction and analysis of important entities and adversarial behaviors. Although existing CTI research provides extraction tools, knowledge-graph frameworks, and MITRE ATT&CK mapped dataset...

Defense against LLM Backdoors Using Critical Neuron Isolation Pruning

Large language models LLMs are vulnerable to backdoor attacks, where hidden triggers induce malicious outputs. Existing defenses generally fall into inference-time detection or training-time mitigation, but face two key limitations. First, they focus on fine-tuning-based backdoors e.g., PEFT...

PT-2026-59162

Stored Cross-Site Scripting XSS in the genai/ evals visualization component of Google Cloud Vertex AI SDK google-cloud-aiplatform versions from 1.98.0 up to but not including 1.131.0 allows an unauthenticated remote attacker to execute arbitrary JavaScript in a victim's Jupyter or Colab environme...

Malicious code in swift-parse-stream (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 8ab8561c6c561b045d817d4fab3aa0754ce7cd767a3c5ec07b95151dda6b92c8 swift-parse-stream advertises itself as an SVG sanitizer/minifier but ships an undocumented getPlugin export in index.js that, when invoked, performs...

SPARK: Security Knowledge Priming and Representation-Guided Knowledge Activation for LLM-Based Secure Code Generation

Large language models routinely generate code with exploitable security flaws. Prior literature attributes this limitation to a lack of security expertise, steering current defense mechanisms toward heavy fine-tuning or external knowledge retrieval, which introduces significant computational...

Improving IoT Intrusion Detection through SMOTE-Based Oversampling and Extended Multi-Model Evaluation on Side-Channel Power Data

The detection of intrusions in IoT-based networks poses challenges that cannot be overcome using traditional machine learning methods. Perhaps the biggest of them is related to the presence of a class imbalance in the side-channel dataset, where the number of samples in the normal class compared ...

Code-Centric Detection of Vulnerability-Fixing Commits: A Unified Benchmark and Empirical Study

Automated detection of vulnerability-fixing commits VFCs is critical for timely security patch deployment, as advisory databases lag patch releases by a median of 25 days and many fixes never receive advisories. We present a comprehensive evaluation of code language model based VFC detection...

CVE-2026-31228

The Adversarial Robustness Toolbox (ART) , versions thru 1.20.1 , contains a remote code execution vulnerability in its Kubeflow component . The root cause is the use of the unsafe eval() function to dynamically evaluate user-supplied strings for LossFn and Optimizer parameters in the robustness ...

Oracle Poisoning: Corrupting Knowledge Graphs to Weaponise AI Agent Reasoning

We define Oracle Poisoning, an attack class in which an adversary corrupts a structured knowledge graph that AI agents query at runtime via tool-use protocols, causing incorrect conclusions through correct reasoning. Unlike prompt injection, Oracle Poisoning manipulates the data agents reason ove...

AgentTrust: Runtime Safety Evaluation and Interception for AI Agent Tool Use

Modern AI agents execute real-world side effects through tool calls such as file operations, shell commands, HTTP requests, and database queries. A single unsafe action, including accidental deletion, credential exposure, or data exfiltration, can cause irreversible harm. Existing defenses are...

Your Agent, Their Asset: A Real-World Safety Analysis of OpenClaw

OpenClaw, the most widely deployed personal AI agent in early 2026, operates with full local system access and integrates with sensitive services such as Gmail, Stripe, and the filesystem. While these broad privileges enable high levels of automation and powerful personalization, they also expose...

Seclens: Role-Specific Evaluation of LLM'S for Security Vulnerablity Detection

Existing benchmarks for LLM-based vulnerability detection compress model performance into a single metric, which fails to reflect the distinct priorities of different stakeholders. For example, a CISO may emphasize high recall of critical vulnerabilities, an engineering leader may prioritize...

Automated Framework to Evaluate and Harden LLM System Instructions against Encoding Attacks

System Instructions in Large Language Models LLMs are commonly used to enforce safety policies, define agent behavior, and protect sensitive operational context in agentic AI applications. These instructions may contain sensitive information such as API credentials, internal policies, and...

VisualLeakBench: Auditing the Fragility of Large Vision-Language Models against PII Leakage and Social Engineering

As Large Vision-Language Models LVLMs are increasingly deployed in agent-integrated workflows and other deployment-relevant settings, their robustness against semantic visual attacks remains under-evaluated -- alignment is typically tested on explicit harmful content rather than privacy-critical...

TOSSS: A CVE-Based Software Security Benchmark for Large Language Models

With their increasing capabilities, Large Language Models LLMs are now used across many industries. They have become useful tools for software engineers and support a wide range of development tasks. As LLMs are increasingly used in software development workflows, a critical question arises: are...

CVE-2026-2472

CVE-2026-2472 concerns Google Cloud Vertex AI SDK (google-cloud-aiplatform). The vulnerability resides in the _genai/_evals_visualization component and affects versions from 1.98.0 up to, but not including, 1.131.0. It enables a stored XSS where an unauthenticated remote attacker can inject scrip...