OpenClaw Agents Can Be Guilt-Tripped Into Self-Sabotage

In a controlled experiment, OpenClaw agents proved prone to panic and vulnerable to manipulation. They even disabled their own functionality when gaslit by humans.

GitHub adds AI-powered bug detection to expand security coverage

GitHub is adopting AI-based scanning for its Code Security tool to expand vulnerability detections beyond the CodeQL static ...
SecurityWeek

From Trivy to Broad OSS Compromise: TeamPCP Hits Docker Hub, VS Code, PyPI

The hackers compromised GitHub Action tags, then shifted to NPM, Docker Hub, VS Code, and PyPI, and teamed with Lapsus$.

Trivy supply-chain attack spreads to Docker, GitHub repos

The TeamPCP hackers behind the Trivy supply-chain attack continued to target Aqua Security, pushing malicious Docker images ...
The Hacker News

⚡ Weekly Recap: CI/CD Backdoor, FBI Buys Location Data, WhatsApp Ditches Numbers & More

Trivy backdoored, FBI buys location data, iOS DarkSword kit, WhatsApp usernames, Langflow RCE, Cisco FMC zero-day & critical ...
IEEE

Beyond Debugging: Can Static Analysis Become a Reality for PLC Software Security?

Abstract: This paper provides an overview of Programmable Logic Controllers (PLCs) and discusses the importance of static analysis for PLC software, highlighting its benefits and challenges. It ...
Forbes

Microsoft Confirms SQL Zero-Day Security Vulnerability—Here’s The Fix

This voice experience is generated by AI. Learn more. This voice experience is generated by AI. Learn more. The Microsoft Security Response Center has confirmed that a SQL Server elevation of ...
Android

OpenAI’s Codex Security: An AI Agent That Hunts Down Vulnerabilities

OpenAI has launched Codex Security, an AI-powered vulnerability scanner, in research preview for ChatGPT Pro, Enterprise, and Edu users. Formerly known as Aardvark, the tool aims to reduce false ...
Reuters

Meta acquires AI agent social network Moltbook

March 10 (Reuters) - Facebook parent Meta Platforms (META.O), opens new tab said on Tuesday it had acquired Moltbook, a social networking platform built for artificial intelligence agents, bringing ...
SecurityWeek

OpenAI Rolls Out Codex Security Vulnerability Scanner

Codex Security, formerly Aardvark⁠, has found hundreds of critical vulnerabilities in tested software in the past month. OpenAI is rolling out a new AI-powered software vulnerability scanner that the ...
The Hacker News

CISA Flags SolarWinds, Ivanti, and Workspace One Vulnerabilities as Actively Exploited

The U.S. Cybersecurity and Infrastructure Security Agency (CISA) on Monday added three security flaws to its Known Exploited Vulnerabilities (KEV) catalog, based on evidence of active exploitation.
Hosted on MSN

OpenAI launches Codex security vulnerability scanner

OpenAI unveiled Codex Security on Friday, an advanced application security tool that detects complex software vulnerabilities. Available in research preview to ChatGPT Enterprise, Business, and Edu ...