faculty-models (>=0.1.0, <=0.1.1), mlflow-faculty (>=0.4.0, <=0.4.3) potentially affected by CVE-2026-2033 via mlflow (1.2.0)

mlflow PYPI version 1.2.0 is affected by a known vulnerability. The following packages have a transitive dependency on mlflow and may be impacted: - faculty-models =0.1.0, =0.4.0, =0.4.3 Source cves: CVE-2026-2033 Source advisory: OSV:PYSEC-2026-2658...

faculty-models (0.2.0), mlflow-faculty (0.5.0) potentially affected by CVE-2026-2033 via mlflow (1.7.2)

mlflow PYPI version 1.7.2 is affected by a known vulnerability. The following packages have a transitive dependency on mlflow and may be impacted: - faculty-models 0.2.0 - mlflow-faculty 0.5.0 Source cves: CVE-2026-2033 Source advisory: OSV:PYSEC-2026-2658...

PT-2026-59205

A vulnerability in the TFSMLayer class of the keras package, version 3.13.0, allows attacker-controlled TensorFlow SavedModels to be loaded during deserialization of .keras models, even when safe mode=True. This bypasses the security guarantees of safe mode and enables arbitrary attacker-controll...

PT-2026-59370

Summary When setting model permissions so that a group has read access to it, intending for other users to use it, those users also can read the model's system prompt. However users may consider their system prompt confidential, so we consider this a security issue. Compare...

AMT-X: Phase-Structured Multi-Turn Red-Teaming with Checklist-Gated Evaluation

Safety evaluation of large language models LLMs relies largely on single-turn attack datasets and single-judge scoring, underestimating risk from adaptive multi-turn adversaries and reporting a single success rate that does not separate partially actionable outputs from those carrying complete...

PT-2026-59399

Summary An internal-only bypass filter parameter is exposed on the /openai/chat/completions and /ollama/api/chat HTTP endpoints via FastAPI query string binding, allowing any authenticated user to append ?bypass filter=true and bypass model access control checks to invoke admin-restricted models...

Agent Hacks Agent: Autoresearch for Production-Agent Red-Teaming

Production LLM agents such as Claude Code and Codex operate over untrusted content, files, commands, and workspace state, making safety failures directly actionable. Red-teaming must therefore keep pace with evolving models and tools. Existing approaches mainly optimize attack success and preserv...

PT-2026-59383

Summary A regular user non-admin can view the system prompt of the model which is set by an admin. Details When a regular user non-admin logs into the application, a http://IP:8080/api/models? web request is initiated by the application and in response, it reveals the system prompt of available...

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge

Large Language Models LLMs are rapidly moving from research settings into the wild, deployed on enterprise infrastructure, personal devices, and edge platforms. While cloud deployments offer scalable compute, concerns over data sovereignty, compliance, latency, and third-party dependence are...

Open WebUI Permission Bypass Privilege Escalation

The vulnerability of the Open WebUI web interface relates to the lack of permission checking for workspace.models.import. Exploiting this vulnerability can allow an attacker, operating remotely, to gain read access, modify data, and enhance their privileges by sending a specially crafted POST...

Large Language Models in Misinformation Ecosystems: Misuse, Defense, and Vulnerability

Large language models LLMs have transformed misinformation from a primarily content-centric problem into a broader ecosystem-level security challenge. When misused, LLMs create risks beyond false content generation, enabling attacks on the social contexts, evidence sources, retrieval corpora, and...

Which Neurons Detect Malicious Code? A Probing Study of LLM Security Knowledge

Background. Large language models LLMs have become increasingly capable of understanding and generating source code, leading to their widespread adoption in software engineering tasks such as code completion, repair, and vulnerability detection. However, despite their strong empirical performance...

Open WebUI Unauth Verification

Confirms Open WebUI /api/config or /api/models without authentication. !/usr/bin/env python3 -- coding: utf-8 -- """Verify Open WebUI unauthenticated config and model access.""" from kittysploit import from lib.protocols.http.httpclient import Httpclient from lib.scanner.http.responsevalidation...

VEXAIoT: Autonomous IoT Vulnerability EXploitation Using AI Agents

Internet of Things IoT systems are inherently vulnerable due to constrained hardware, outdated firmware, and insecure default configurations, creating a need for scalable and adaptive security testing approaches. While recent adoptions of Large Language Model LLM agents have demonstrated promise ...

Using LLMs to Adjudicate Static-Analysis Alerts with Error Reduction Techniques

Static analysis is widely used for finding security weaknesses in source code before deployment, but it often produces far more alerts than analysts can review. We study how well large language models LLMs can adjudicate classify as a real bug or a false alarm static-analysis alerts. We use two...

Evaluating AI Models' Capability to Automate Voice Phishing Attacks

Voice phishing vishing attacks have traditionally been limited by the need for human operators. The rapid emergence of high-quality AI voice synthesis and large language models LLMs reduces this bottleneck and enables scalable, automated scams. In this paper, we conduct a large-scale survey...

EUVD-2025-210448

Unauthorized use of Kyocera printers, allows all information stored in the Kyocera address book to be exported. The security measure that encrypts incoming data ian be bypassed with this vulnerability, allowing encrypted data to be decrypted. Passwords and other sensitive information can be...

CVE-2026-57031

Summary of CVE-2026-57031 (Junos OS MX Series): A vulnerability in the packet forwarding engine (PFE) of Juniper Networks Junos OS on MX Series devices allows adjacent subscribers configured on static interfaces to bypass ingress firewall filters, disabling both protocol-level and upstream bandwi...

CVE-2026-59222 Open WebUI: /api/v1/channels/{id}/members exposes full user model including sensitive credentials

Open WebUI is an extensible, feature-rich, and user-friendly self-hosted AI platform. From 0.7.0 before 0.10.0, GET /api/v1/channels//members returned full UserModelResponse objects for channel members, including settings.ui.toolServers.key and webhook configuration, allowing a normal channel...

CVE-2026-59213 Open WebUI: Cross-user model-list exposure via static cache key in get_all_models (aiocache key= vs key_builder= misuse)

Open WebUI is an extensible, feature-rich, and user-friendly self-hosted AI platform. From 0.6.27 before 0.10.0, getallmodels handlers in routers/openai.py and routers/ollama.py passed a lambda to aiocache key instead of keybuilder, causing permission-filtered per-user model lists to share a stat...