ChatGPT's new Lockdown Mode can stop prompt injection - here's how it works

Lockdown Mode enhances the protection against prompt injections and other advanced threats. With this setting enabled, ChatGPT is limited in the ways it can interact with external systems and data, ...
IEEE

Attack Detection of Cyber-Physical Systems With Two-Channel False Data Injection Attacks

Abstract: This paper addresses the attack detection problem for cyber-physical systems subject to false data injection attacks. A novel detection framework is developed for cyber-physical systems ...
The Hacker News

OpenClaw Integrates VirusTotal Scanning to Detect Malicious ClawHub Skills

OpenClaw integrates VirusTotal Code Insight scanning for ClawHub skills following reports of malicious plugins, prompt injection & exposed instances.
SecurityWeek

Cryptominers, Reverse Shells Dropped in Recent React2Shell Attacks

The majority of the 1.4 million React2Shell exploitation attempts GreyNoise saw in a week deployed cryptominers and reverse shells.
Ars Technica

The rise of Moltbook suggests viral AI prompts may be the next big security threat

On November 2, 1988, graduate student Robert Morris released a self-replicating program into the early Internet. Within 24 hours, the Morris worm had infected roughly 10 percent of all connected ...
VentureBeat

Infostealers added Clawdbot to their target lists before most security teams knew it was running

Clawdbot's MCP implementation has no mandatory authentication, allows prompt injection, and grants shell access by design. Monday's VentureBeat article documented these architectural flaws. By ...
The Washington Post

Rep. Ilhan Omar says ‘fear and intimidation doesn’t work on me’ after town hall attack

Rep. Ilhan Omar (D-Minnesota), during a news conference Wednesday evening, connected President Donald Trump’s rhetoric and an attack this week , in which a man used a syringe to spray an unknown ...
Forbes

When AI Agents Turn Against You: The Prompt Injection Threat Every Business Leader Must Understand

This voice experience is generated by AI. Learn more. This voice experience is generated by AI. Learn more. Prompt injection attacks can manipulate AI behavior in ways that traditional cybersecurity ...
MIT Technology Review

Rules fail at the prompt, succeed at the boundary

Why the first AI-orchestrated espionage campaign changes the agent security conversation Provided byProtegrity From the Gemini Calendar prompt-injection attack of 2026 to the September 2025 ...
SecurityWeek

‘PackageGate’ Flaws Open JavaScript Ecosystem to Supply Chain Attacks

Half a dozen vulnerabilities in the JavaScript ecosystem’s leading package managers — including NPM, PNPM, VLT, and Bun — could be exploited to bypass supply chain attack protections, according to ...
devdiscourse

Conspiracy and Betrayal: HIV Injection Attack on Doctor

In a shocking turn of events, four individuals have been arrested for allegedly plotting to inject a doctor with HIV-infected blood in a bid to harm her. The incident, which occurred in Kurnool, ...