30 matches found
alignment-cage-challenge-2
Alignment of Autonomous Cyber Defense Agents via Adaptive Policy Shaping Code for our paper Alignment of Autonomous Cyber Defense Agents via Adaptive Policy Shaping. This repository extends CybORG CAGE Challenge 2 to study how autonomous defenders can be steered towards operational priorities whi...
CVE-2026-87575-CVE-2026-87606-CVE-2026-87491-and-CVE-2026-85046.-Escape-the-v8-carcass.
CVE-2026-85046 + CVE-2026-87491 + CVE-2026-87606 + CVE-2026-87575 Talk about a giant pain to sneak a path out of the renderer. 550 mg of caffiene and going up and down chrome CVE's all night, you too can bounce out of the renderer. CVE-2026-85046 corrupts a Float64Array for V8-cage read/write...
yolo-cage
yolo-cage: autonomous coding agents that do no harm You're a responsible engineer. You'd never just let an AI run roughshod through your most sensitive systems and codebases. That's why you'd never just shut off the safeguards for a tool like Claude Code. It asks permission for every dangerous...
No One Architecture Fits All: A Cross-Environment Evaluation of Hierarchical Red Team Agents
Autonomous red team agents increasingly stress-test AI-enabled cyber defenses by planning strategy and executing multistage attacks. Reinforcement learning RL and large language models LLMs offer complementary mechanisms for the planning and execution such agents require, and prior work has...
Exploit for Out-of-bounds Write in Google Chrome
CVE-2026-85046 + CVE-2026-87491 + CVE-2026-87606 + CVE-2026-87...
CVE-2026-53231
In the Linux kernel, the following vulnerability has been resolved: net: phy: don't try to setup PHY-driven SFP cages when using genphy We don't have support for PHY-driver SFP cages with the genphy code. On top of that, it was found by sashiko that running sfpbusaddupstream for genphy deadlocks,...
WS-2019-0406
cage-js contains malicious code. The malware downloads and runs a script from a remote server as a postinstall script...
EUVD-2023-29867
Malicious code in bioql PyPI...
MAL-2025-43684 Malicious code in cage-farm-current (npm)
The package cage-farm-current was found to contain malicious code...
Malicious code in cage-farm-current (npm)
The package cage-farm-current was found to contain malicious code...
MAL-2025-16429 Malicious code in cage-js (npm)
The package cage-js was found to contain malicious code...
MAL-2025-26810 Malicious code in mp3-file-zip-d-ownload-82223-cage-tropical-48dqs-lilnlq (npm)
The package mp3-file-zip-d-ownload-82223-cage-tropical-48dqs-lilnlq was found to contain malicious code...
Malicious code in cage-js (npm)
The package cage-js was found to contain malicious code...
CVE-2023-25980
Cross-Site Request Forgery CSRF vulnerability in CAGE Web Design | Rolf van Gelder Optimize Database after Deleting Revisions plugin = 5.1 versions...
Large Language Models Are Autonomous Cyber Defenders
Fast and effective incident response is essential to prevent adversarial cyberattacks. Autonomous Cyber Defense ACD aims to automate incident response through Artificial Intelligence AI agents that plan and execute actions. Most ACD approaches focus on single-agent scenarios and leverage...
These Guys Hacked AirPods to Give Their Grandmas Hearing Aids
Three technologists in India used a homemade Faraday cage and a microwave oven to get around Apple’s location blocks...
CVE-2023-25980
Cross-Site Request Forgery CSRF vulnerability in CAGE Web Design | Rolf van Gelder Optimize Database after Deleting Revisions plugin = 5.1 versions...
CVE-2023-25980
Cross-Site Request Forgery CSRF vulnerability in CAGE Web Design | Rolf van Gelder Optimize Database after Deleting Revisions plugin = 5.1 versions...
