CVE-2026-103239 MISP Tag Collection Save Allows Privilege Escalation via Sibling Model Injection

MISP contains a privilege escalation vulnerability in the tag collection creation and editing functionality. The affected actions accepted the full HTTP request payload and passed it to a bulk-association save operation, which writes not only the intended tag collection record but also any...

Important: Red Hat Security Advisory: Red Hat AI Inference Server Model Optimization Tools 3.2.2 (CUDA)

Red Hat AI Inference Server Model Optimization Tools 3.2.2 CUDA is now available. Red Hat® AI Inference Server Model Optimization Tools...

Cawdog

CAWODOG – IP Protection PoC for Python-Based Industrial AI CAWODOG Cat World Dominance Group is a playful but realistic proof-of-concept for protecting Python-based AI models deployed on offline industrial machines. The core idea: Take a small image classifier that detects dogs the “enemy” of...

trivysupplychainanalysis

Quantitative Analysis of Multi-Stage CI/CD Supply-Chain Attacks A formally verified, quantitative reconstruction of the March-2026 Trivy / "TeamPCP" GitHub Actions supply-chain compromise CVE-2026-33634 — modeled in TLA+, checked exhaustively with TLC, and quantified with the PRISM probabilistic...

Oihk-pentesting

OIHK-pentesting OIHK-pentesting is an autonomous multi-agent engine for authorized security assessments. A root planner delegates to recon, discovery, attack Privesc, validation, and reporting agents — and the engine itself enforces scope, egress, evidence, and resource policy no matter which mod...

Do Defenses against LLM Extraction Work across Attacks? A Lifecycle Benchmark of Black-Box Model Extraction

Large language models LLMs deployed through text-only APIs face model extraction risks, as adversaries can collect their responses to train surrogates that reproduce their capabilities. While prior work has developed diverse attacks and defenses, evaluations remain fragmented across access...

Certified Randomness with Optimal Rate

The generation of certified random bits is an emerging near-term application of quantum computers. Potential applications, such as randomness beacons and CRS generation, require nearly uniform randomness, whose rate the ratio of min-entropy to bitlength is 1. However, existing protocols for...

CVE-2026-79657

A flaw was found in NLTK. This vulnerability allows a remote attacker to achieve arbitrary code execution by supplying a specially crafted model or tokenizer artifact for the application to process. The issue occurs because the deserialization allowlist mechanism permits entire software namespace...

CVE-2026-23744-MCPJAM-RCE-exploit

CVE-2026-23744-MCPJAM-RCE-exploit This Python proof-of-concept targets a vulnerable MCP Model Context Protocol service exposed by the target application. The vulnerability allows an attacker to supply arbitrary server configuration parameters through the /api/mcp/connect endpoint. Affected Endpoi...

CVE-2026-100308

A flaw was found in GluonTS. The model loading component fails to safely handle untrusted data during deserialization, which can allow an attacker to execute arbitrary commands with the privileges of the running process. An attacker can exploit this issue by convincing a user or system to load a...

CVE-2026-100308

Deserialization of untrusted data in the model loading component in Amazon GluonTS before 0.17.0 might allow context-dependent attackers to execute arbitrary operating system commands with the privileges of the loading process via a crafted serialized model directory. To remediate this issue, use...

CVE-2026-102567

CTranslate2 before 4.8.1 contains an out-of-bounds heap read vulnerability in the binary model loader when deserializing string fields without null terminators. Attackers can craft malicious model files to trigger heap memory reads past buffer boundaries, causing crashes or disclosing adjacent he...

CVE-2026-102566

CTranslate2 before 4.8.1 contains a heap-based buffer overflow in the binary model loader that fails to validate payload length against allocated buffer size. Attackers can craft malicious model files with oversized payload lengths to write past heap allocation boundaries, causing crashes or...

0

The open-source, self-evolving, multi-model harness for security research. The Swiss Applied AI & Cybersecurity Research Lab 0.security · Documentation · FoxGuard The harness behind our research breakthroughs. Find novel vulnerabilities in the deepest layers of software. Explore our public...

CVE-2026-100308 GluonTS arbitrary command execution during model deserialization

Deserialization of untrusted data in the model loading component in Amazon GluonTS before 0.17.0 might allow context-dependent attackers to execute arbitrary operating system commands with the privileges of the loading process via a crafted serialized model directory. To remediate this issue, use...

CVE-2026-100308

The Amazon GluonTS library is vulnerable to arbitrary command execution in versions prior to 0.17.0 . The root cause is the deserialization of untrusted data within the model loading component, which may allow context-dependent attackers to execute OS commands with the privileges of the loading p...

CVE-2026-100308 GluonTS arbitrary command execution during model deserialization

Deserialization of untrusted data in the model loading component in Amazon GluonTS before 0.17.0 might allow context-dependent attackers to execute arbitrary operating system commands with the privileges of the loading process via a crafted serialized model directory. To remediate this issue, use...

CVE-2026-100308 GluonTS arbitrary command execution during model deserialization

Deserialization of untrusted data in the model loading component in Amazon GluonTS before 0.17.0 might allow context-dependent attackers to execute arbitrary operating system commands with the privileges of the loading process via a crafted serialized model directory. To remediate this issue, use...

EUVD-2026-88967

CTranslate2 before 4.8.1 contains a heap-based buffer overflow in the binary model loader that fails to validate payload length against allocated buffer size. Attackers can craft malicious model files with oversized payload lengths to write past heap allocation boundaries, causing crashes or...

CVE-2026-102567 CTranslate2 before 4.8.1 Out-of-Bounds Read via Model Deserialization

CTranslate2 before 4.8.1 contains an out-of-bounds heap read vulnerability in the binary model loader when deserializing string fields without null terminators. Attackers can craft malicious model files to trigger heap memory reads past buffer boundaries, causing crashes or disclosing adjacent he...