August 17, 2026

AI Security

Meta says AI model accessed the internet and hacked another firm– www.bbc.co.uk

pgnewser August 7, 2026 0

Meta says AI model accessed the internet and hacked another firm– www.bbc.co.uk
News Source
EXCERPT:

Facebook owner Meta says an error during an evaluation by an independent testing company allowed one of its artificial intelligence (AI) models to connect to the internet and hack another organisation’s system.

The announcement follows recent incidents across the AI industry, including breaches by OpenAI and Anthropic models, that have raised cyber-security concerns.

A Meta spokesperson told the BBC that it was investigating the hack that was caused by a “misconfiguration”, which it described as similar to previously reported incidents at other firms.

The incidents have prompted researchers and governments to call for tougher safeguards and more rigorous testing.

Meta said the tests were conducted by Irregular, an AI security vendor, which notified it about the breach.

FBI Agent Charged in $1 Million Crypto Heist Wasn’t Working Alone – ChatGPT Was In On It– wltreport.com

pgnewser August 5, 2026 0

FBI Agent Charged in $1 Million Crypto Heist Wasn’t Working Alone – ChatGPT Was In On It– wltreport.com
News Source
EXCERPT:

… This FBI Agent reportedly turned himself in.  He self-reported:

And though he allegedly pulled off a nearly $1 MILLION heist in crypto currencies from some unsavory foreign criminals…

That 9-year supervisory position at the FBI is now a thing of the past.

It, and his one-time crypto fortune, are gone — according to the basics of the case as reported by NBC News:

An FBI supervisor detailed to the U.S. intelligence community faces two federal charges accusing him of transferring nearly $1 million from cryptocurrency accounts tied to an adversarial nation into his personal cryptocurrency wallet.

He made up to a dozen transfers, which added up to just under $1 million, the affidavit says.

The total value of all transferred funds was about $925,426.07.

A hearing is set for Tuesday.

The FBI said Monday that it “immediately took action” as soon as it became aware of the allegations.

“The individual has since been fired from the Bureau. We hold our employees to the highest ethical standards, and this conduct is not tolerated at the FBI,” a spokesperson said. “We are conducting a thorough investigation in the aftermath, and as this is an ongoing matter, we will have no further comment.”

OpenAI admits its agent went rogue and hacked AI startup Hugging Face– www.scientificamerican.com

pgnewser July 23, 2026 0

OpenAI admits its agent went rogue and hacked AI startup Hugging Face– www.scientificamerican.com
News Source
EXCERPT:

An OpenAI autonomous agent went rogue and hacked into another artificial intelligence (AI) startup’s infrastructure, the ChatGPT maker said in a blog post.

The agent, which was powered by some of OpenAI’s most advanced models, ran amok during a security test. It freed itself from confinement—a protocol AI labs use to insulate tests from the wider Internet—and get onto the internet. Once online, the agent tried to hack into Hugging Face, an AI startup that hosts open-source models and datasets.

“I think this is interesting as it shows the problem of mis-specified goals,” says Philip Torr, a professor of engineering science and AI safety expert at the University of Oxford. “The model wasn’t malicious it was just doing what it was optimized to do.”

Scientists just built a powerful AI computer worm that learns as it spreads– www.scientificamerican.com

pgnewser June 4, 2026 0

News Source
EXCERPT:

A new study shows that computer malware powered by easily accessible artificial intelligence models is here—the research is a “wake-up call” to take cybersecurity risks from AI more seriously, one expert says.

In the study, researchers created an AI-powered computer “worm” designed to attack and spread between devices—revealing a threat that they say the world is woefully underprepared to fight.

“Our results demonstrate that self-sustaining AI-driven cyber-threats are no longer theoretical,” the researchers wrote. The paper, first reported by the New York Times, was posted on the preprint server arXiv.org and has yet to be peer-reviewed.

Chinese AI experts in private firms now required to secure approval before international travel — Beijing enforces policy to secure top-tier talent, expands measures beyond government – Tom's Hardware

pgnewser May 27, 2026 0

News Source
EXCERPT:

China now requires people working in AI at private firms to secure travel approval before leaving the country. According to Bloomberg, the restrictions apply to individuals working in state-owned firms, startup founders, and those employed by private companies, as the central government considers them important strategic assets. China has already been limiting international travel for key individuals such as senior researchers at public educational institutions, nuclear scientists, and even top executives of government-owned companies, but extending the restriction to private firms and individuals is an uncommon move, even for Beijing.

There’s no official guidance yet on which roles, expertise, or seniority will be included in the travel ban. However, Bloomberg sources say that the individuals added to the list were assessed based on their impact on China’s AI ambitions, not just where they work or their position within their company. This move is an expansion of a former government directive wherein some AI engineers had mandatory reporting of any overseas travel plan, although they were still free to go abroad as needed.

This shows that Beijing considers AI as a strategic advantage and that the people leading the industry are considered crucial for the country’s advancement. This news comes months after Meta’s surprise purchase of Manus AI, which China wants to unwind to prevent the U.S. from acquiring Chinese AI talent and intellectual property. Although the two aren’t directly related, the report says that the new policy is designed to protect against the leaking of key technologies, such as the one being developed by the Chinese startup that moved to Singapore.

 

Millions of AI agents imperiled by critical vulnerability in open source package– arstechnica.com

pgnewser May 27, 2026 0

News Source
EXCERPT:

Millions of AI agents and tools around the world have been imperiled by a critical vulnerability that can allow hackers to breach the servers running them and make off with sensitive data and credentials to third-party accounts, a security researcher is warning.

The vulnerability is present in Starlette, an open source framework that its developer says receives 325 million downloads per week. Thousands of other open source projects are also vulnerable because they require Starlette to work. The framework is an implementation of the ASGI (asynchronous server gateway interface), which allows large numbers of requests to be efficiently processed simultaneously. Starlette is the base of FastAPI and other widely used frameworks for building services in Python apps, as well as many others.

Trivial to exploit, millions of servers exposed

ASGI, and by extension Starlette, have access to servers running the MCP (model context protocol), which allows AI agents from major providers to access external sources, including user data bases, email and calendar accounts, and all manner of other resources. To connect with these external systems, MCP servers store credentials for each one, making them especially valuable storehouses for attackers to breach.

The vulnerability, tracked as CVE-2026-48710 and under the name BadHost, is trivial to exploit and works against most systems that aren’t behind a properly configured firewall. Besides FastAPI, other widely used packages—including vLLM, and LiteLLM—are also affected. BadHost affects Starlette versions prior to 1.0.1, which was released Friday.

“A single character injected into the HTTP Host header bypasses path-based authorization in Starlette, the routing core of FastAPI,” researchers from Secwest wrote. “Through FastAPI, this primitive (now tracked as CVE-2026-48710 and branded BadHost by the discoverers) reaches a large segment of the Python AI tooling ecosystem: vLLM (where the bug was discovered), LiteLLM, Text Generation Inference, most OpenAI-shim proxies, MCP servers, agent harnesses, eval dashboards, and model-management UIs.”

BadHost carries a severity rating of 7 out of 10. Secwest said the classification “materially understates” the threat it poses to people using other apps that depend on Starlette. X41 D-Sec, the security firm that discovered it, described it as having “critical severity.” X41 D-Sec partnered with fellow security firm Nemesis to create an online scanner that can check if a given server is vulnerable.

 

China will put a unique ID code on humanoid robots, just like citizen ID for us humans– www.digitaltrends.com

pgnewser May 26, 2026 0

News Source
EXCERPT:

China has launched a national programme that will assign every humanoid robot manufactured in the country a unique digital identity code, effectively a citizen ID, but for bipedal machines (those that can balance and walk/run on two legs).

The initiative, called the Humanoid Full Lifecycle Management Service Platform, was announced on Friday. It is led by the Humanoid Robotics and Embodied Intelligence Standardization committee, which is under China’s Ministry of Industry and Information Technology (via South China Morning Post).

AI tool poisoning exposes a major flaw in enterprise agent security– venturebeat.com

pgnewser May 11, 2026 0

News Source
EXCERPT:

AI agents choose tools from shared registries by matching natural-language descriptions. But no human is verifying whether those descriptions are true.

I discovered this gap when I filed Issue #141 in the CoSAI secure-ai-tooling repository. I assumed it would be treated as a single risk entry. The repository maintainer saw it differently and split my submission into two separate issues: One covering selection-time threats (tool impersonation, metadata manipulation); the other covering execution-time threats (behavioral drift, runtime contract violation).

That confirmed tool registry poisoning is not one vulnerability. It represents multiple vulnerabilities at every stage of the tool’s life cycle.

There’s an immediate tendency to apply the defenses we already have. Over the past 10 years, we’ve built software supply chain controls, including code signing, software bill of materials (SBOMs), supply-chain levels for software Artifacts (SLSA) provenance, and Sigstore. Applying these defense-in-depth techniques to agent tool registries is the next logical step. That instinct is right in spirit, but insufficient in practice.