Hugging Face Has a Deepfake Nudes Problem

Researchers tested top image editing models on Hugging Face and found they could easily create explicit deepfakes—and 1,000 image editing prompts show how people use the software...

ethical-hacking-elewayte-projects

Ethical Hacking Projects — Elewayte Externship Penetration te...

exploitarium

Statement This repo was incomplete when published. In regar...

PYSEC-2026-2554 Kolibri has Unauthenticated Server-Side Request Forgery (SSRF) in RemoteFacilityUserViewset

Summary Several Kolibri API endpoints accept an unvalidated baseurl parameter and fetch attacker-controlled URLs from the Kolibri server, reflecting the response body back to the caller. The original report identified two endpoints on the RemoteFacilityUser viewsets; remediation review found two...

patchtriage

PatchTriage !CIhttps://github.com/d01ki/patchtriage/actio...

The Language of AI Could Change How Humans Speak

Because of the way they are trained, large language models capture only a slice of human language. They're trained on the written word, from textbooks to social media posts, and our speech as captured in movies and on television. These models have minimal access to the unscripted conversations we...

PT-2026-51189

A vulnerability was found in AOMEI Dynamic Disk Manager up to 10.10.1. This issue affects some unknown processing in the library ddmdrv.sys of the component Kernel Driver. Performing a manipulation results in improper access controls. The attack must be initiated from a local position. The exploi...

Anthropic’s Project Glasswing Update

In April, Anthropic initated Project Glasswing. The idea was to let companies use their new model to find and fix vulnerabilities in their own software. It was a fantastic PR move, and so many press outlets have uncritically parroted Anthropic's claims that it's now common wisdom that Mythos is...

Updating the taxonomy of failure modes in agentic AI systems: What a year of red teaming taught us

In this article 1. Why the Taxonomy Needed Updating 2. Seven new failure modes 3. Operational findings: What red teaming showed 4. New mitigations 5. What to do this quarter When the Microsoft AI Red Team published the Taxonomy of Failure Modes in Agentic AI Systems in April 2025, the goal was a...

Updating the taxonomy of failure modes in agentic AI systems: What a year of red teaming taught us

In this article 1. Why the Taxonomy Needed Updating 2. Seven new failure modes 3. Operational findings: What red teaming showed 4. New mitigations 5. What to do this quarter When the Microsoft AI Red Team published the Taxonomy of Failure Modes in Agentic AI Systems in April 2025, the goal was a...

Bastet: A Fine-Grained Expert-Labeled Dataset for DeFi Smart Contract Vulnerability Detection

Smart contract vulnerabilities in Decentralized Finance DeFi protocols resulted in over 1.49 billion USD in confirmed losses in 2024 alone, across 192 incidents 1. As LLM-based vulnerability detection emerges as a promising approach to address these threats, the quality of evaluation datasets has...

snyk-agentic-appsec-poc

Snyk Agentic AppSec POC Proof of concept demonstrating autono...

Quality and Security Signals in AI-Generated Python Refactoring Pull Requests

As AI agents increasingly contribute to code development and maintenance, there is still limited empirical evidence on the quality and risk characteristics of their changes in real-world projects, particularly for refactoring-oriented contributions. It remains unclear how agent-authored refactori...

eip-mcp

Exploit Intel Platform MCP Server Package/command: eip-mcp...

offsec-skills

offsec-exploit-research Elite adaptive whitebox exploit resea...

Windows-pentest-lab

Windows-pentest-lab Penetration testing and vulnerability asse...

PickleFuzzer: A Case Study in Fuzzing for Discrepancies between Python Pickle Implementations

Python's native serialization protocol, pickle, is a powerful but insecure format for transferring untrusted data. It is frequently used, especially for saving machine learning models, despite known security challenges. While developers sometimes mitigate this risk by restricting imports during...

Microsoft's MDASH AI System Finds 16 Windows Flaws Fixed in Patch Tuesday

Microsoft has unveiled a new multi-model artificial intelligence AI-driven system called MDASH to facilitate vulnerability discovery and remediation at scale, adding that it's being tested by some customers as part of a limited private preview. MDASH, short for m ulti-mod el a gentic s canning h...

Introducing Wiz Audit History: Track Every Change Across your Environment

Wiz Audit History is now GA, providing a continuous, cross-cloud timeline of changes to resource configurations and findings to accelerate incident response and simplify compliance...

Bringing AI Code Security into Qualys ETM

A first-class data model for the next generation of findings AI-driven code security is becoming a real category. Anthropic's Claude Code Security and OpenAI's Codex Security are the leading examples, and more will follow. These tools reason about source code at a depth that traditional SAST cann...