20537 matches found
PT-2026-40125
Name of the Vulnerable Software and Affected Versions Ludwig framework versions prior to 0.10.5 Description The model serving component is subject to insecure deserialization. When initiating a model server via the ludwig serve command, the framework utilizes the torch.load function to load model...
Iterative Audit Convergence in LLM-Managed Multi-Agent Systems: A Case Study in Prompt Engineering Quality Assurance
Prompt specifications for multi-agent large language model LLM systems carry data contracts and integration logic across many interdependent files but are rarely subjected to structured-inspection rigor. This paper reports a single-system empirical case study of iterative, agent-driven auditing...
CVE-2026-31224
The snorkel library thru v0.10.0 contains an insecure deserialization vulnerability CWE-502 in the MultitaskClassifier.load method of the MultitaskClassifier class. The method loads model weight files using torch.load without enabling the security-restrictive weightsonly=True parameter. This...
Reconstruction of Personally Identifiable Information from Supervised Finetuned Models
Supervised Finetuning SFT has become one of the primary methods for adapting a large language model LLM with extensive pre-trained knowledge to domain-specific, instruction-following tasks. SFT datasets, composed of instruction-response pairs, often include user-provided information that may...
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 ...
SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces
Reusable skills are becoming a common interface for extending large language model agents, packaging procedural guidance with access to files, tools, memory, and execution environments. However, this modularity introduces attack surfaces that are largely missed by existing safety evaluations: eve...
PT-2026-40058
The load model function in the neural magic training.py script of the optimate project in commit a6d302f912b481c94370811af6b11402f51d377f 2024-07-21 is vulnerable to insecure deserialization CWE-502. When a user provides a single model file path e.g., .pt or .pth via the --model command-line...
CVE-2026-31218
The optimate project, an AI model optimization tool library developed by Nebuly, contains an insecure deserialization vulnerability (CWE-502) in the _load_model() function of the neural_magic_training.py script (commit a6d302f912b481c94370811af6b11402f51d377f). The root cause is the failure to en...
CVE-2026-31217
The loadmodel function in the neuralmagictraining.py script of the optimate project in commit a6d302f912b481c94370811af6b11402f51d377f 2024-07-21 allows arbitrary code execution. When a user supplies a directory path via the --model command-line argument, the function reads a module.py file from...
CVE-2026-31238
The Ludwig framework thru 0.10.4 is vulnerable to insecure deserialization CWE-502 in its model serving component. When starting a model server with the ludwig serve command, the framework loads model weight files using torch.load without enabling the security-restrictive weightsonly=True...
CTFusion: A CTF-Based Benchmark for LLM Agent Evaluation
Recent advances in Large Language Models LLMs have enabled agentic systems for complex, multi-step tasks; cybersecurity is emerging as a prominent application. To evaluate such agents, researchers widely adopt Capture The Flag CTF benchmarks. However, current CTF benchmarks reuse existing...
MINI-GQ35-RX9M-X369
Bulletin has no description...
MINI-W46H-24X5-MPFC
Bulletin has no description...
MINI-P72F-5CRJ-32FW
Bulletin has no description...
MINI-95G3-M35W-G493
Bulletin has no description...
MINI-6XMC-299M-GP66
Bulletin has no description...
MINI-57VP-2R25-GRC3
Bulletin has no description...
MINI-X342-RFMJ-JPXF
Bulletin has no description...
CVE-2026-43900 DeepChat: Persistent DOM XSS via HTML Entity Encoding in `<antArtifact>` SVG Rendering (Bypass of `svgSanitizer.ts`)
DeepChat is an open-source artificial intelligence agent platform that unifies models, tools, and agents. Prior to v1.0.4-beta.1, a Cross-Site Scripting XSS vulnerability exists due to a discrepancy between the backend validation layer and the frontend browser rendering engine. The SVGSanitizer...
EUVD-2026-29180
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...