OpenAI on Tuesday revealed that it paused reinforcement learning ( RL ) training for its latest artificial intelligence (AI) models for two weeks while it shored up additional defenses and increased the scope of its monitoring to avert another Hugging Face-like incident . “Clicking it opened a browser drawn inside the real browser. The fake address bar displayed trusted origins such as accounts.google.com or an Okta tenant, while the real browser remained on the phishing domain.” “Behind the interface, the platform kept every passw… The company said it also found an additional 5,500 verified software vulnerabilities between April and October 2026 through open-source scanning efforts. They mark the latest point in a five-year arc where resilience, AI governance, human risk, and board scrutiny are converging inside the systems where work actually happens. “In this activity, the threat actor leveraged ARTEX, a recently released open-source agentic penetration testing (pentesting) tool developed in China, alongside large language models (LLMs),” the cybersecurity company said .
Its functionality includes credential theft from Chrome and Firefox, GDI-based screenshot capture, file enumeration and retrieval, PowerShell remote shell execution, system fingerprinting, and encrypted command-and-control (C2) communications. ASHVEIN, which its developers internally refer to as “TelemetryBrowser,” brings together credential theft, surveillance, and remote-control capabilities. According to TrendAI, the malware has been put to use in attacks targeting Ukrainian government personnel. Some attacks involve several stages, careful timing, and plenty of tricks.
“We have implemented universal monitoring for risky actions and misalignment across all agentic applications of Astra, including training and evaluation. Monitors evaluate the model’s Chain of Thought and trigger a security re… If teams can suddenly create many times more code, security can also end up with many more components, dependencies, findings, and fixes to manage. But security teams still have to review vulnerabilities, manage dependencies, prioritize fixes, and control risk at human speed.
Defenders Reluctant to Deploy Agentic AI as a Cybersecurity Tool
- The employee followed its advice, inadvertently making a large volume of sensitive data available to unauthorized engineers for over two hours.
- The work, released as a preprint on August 10, 2026, tests the technique in a simulated six-agent coding collaboration and in a chain of paired agents modeled on OpenClaw , the open-source autonomous assistant formerly known as Clawdbot and Moltbot .
- The proposal would require AI developers to ensure their systems include the “technical capability for a human operator to shut down the system.” The bill would require the Department of Homeland Security to issue regulations to ensure compliance with the requirement.
- Shadow AI is the unapproved use of AI tools Shady AI is when employees use approved AI tools in unapproved, unexpected, or poorly governed ways Shadow AI happens outside the organization’s visibility.
- CloudSEK has published the dataset as a public lookup , searchable by name or domain and filterable by confidence.
Cybersecurity researchers have disclosed details of a “human-operated phishing platform” that impersonates advertising products for artificial intelligence (AI) chatbots like Google Gemini, Anthropic Claude, OpenAI ChatGPT, Perplexity, Meta Muse, and Manus. “Of these verified vulnerabilities, more than https://dnews7.com/hitop-is-a-modern-http-testing-tool-with-many-advantages.html 33,000 have so far been rated as critical- or high-severity,” Anthropic said . The financially motivated campaign, dubbed Canto Incognito , has been found to install cryptocurrency miners, including XMRig and Iron, and connects victims to Kryptex, a Russian cryptocurrency mining service.
With AI accelerating reconnaissance, exploitation of vulnerabilities, and privilege escalation, attackers can move through systems faster than security teams can investigate. Latest vulnerabilities, agent threats, and research disclosures. Sens. Michael Bennet (D-Colo.) and Peter Welch (D-Vt.) introduced the AI Regulatory Act last week. Also last week, Sens. Brian Schatz (D-Hawaii) and Mark Warner (D-Va.) introduced the Artificial Intelligence Risk Management and Security Act. The proposal would require AI developers to ensure their systems include the “technical capability for a human operator to shut down the system.” The bill would require the Department of Homeland Security to issue regulations to ensure compliance with the requirement. “If Democrats regain control of the House, technology companies should expect increased scrutiny https://autonow.net/api-testing-to-ensure-software-quality-and-reliability-with-postman.html of AI development, safety practices, competition, content moderation, and data privacy, including a renewed push to bring technology executives before congressional committees to testify on these issues,” they wrote.
