Aggregated from vendor advisories, security research, and industry publications.
Google deleted three AI agent workflows from its Agent Development Kit (ADK) Python repository. Pillar Security showed that a public GitHub issue could manipulate a triage agent into triggering a privileged code-fixing agent. The researchers said the public agent could be prompt-injected into posting /adk-issue-fix as adk-bot. They identified the bot as a collaborator, so that comment satisfied
A crafted prompt to a low-privilege Google ADK agent could be used to pass a malicious hand-off comment to a privileged agent. The post Gemini Agent-to-Agent Attack Method Exposed …
cPanel has patched a flaw that let an authenticated hosting customer execute SQL in the database's root context, crossing the privilege boundary between a cPanel account and the se…
And it’s personal information (alternate link): The exposed data includes an AI-powered therapy app that someone appears to have vibe-coded, notes on meetings, and a dashboard some…
Over 24,000 internet-accessible server-management interfaces disclose authentication hashes before login. The post Decades-Old BMC Vulnerability Exposes Thousands of Data Centers t…
A new Russian loader-as-a-service (LaaS) codenamed DOUBLECUP has been using ClickFix lures as a way to stage malware-laced PNG images in victims' browser cache and ultimately deliv…
An extortion group stole personal, financial, and medical information from the hospital’s network. The post 150,000 Impacted by Madera Community Hospital Data Breach appeared first…
Proposals span AI productivity scores, keystroke logging, biometrics, and other ways to watch workers
The U.S. Cybersecurity and Infrastructure Security Agency (CISA) on Monday added a high-severity security flaw impacting N-able N-central to its Known Exploited Vulnerabilities (KE…
Newer social engineering techniques help attackers ignore entrenched security controls and limit the evidence they leave behind.
Muskmobiles subject to 11 recalls get the launchpad rescue mission currently handled by vehicles that can survive land mine blasts
The biggest single reward paid out by Microsoft between July 1, 2025, and June 30, 2026, was $200,000. The post Microsoft Bug Bounty Program: $20 Million Paid to 500 Researchers ap…
Automates bug bounty triage with Sonnet for $58 a month, CSO says Mythos would cost $200k
Beijing's new rules also protect against copying local chip designs
The grants will help local governments assess and improve cyber defenses amid a multistate campaign targeting water and wastewater infrastructure. The post New York Awards $9 Milli…
Microsoft has linked a global campaign targeting hospitality Wi-Fi networks to the Russian threat actor Midnight Blizzard, also known as APT29. [...]
Security researchers have discovered three attacks that allow malware on already-compromised Windows devices to abuse Google Password Manager's synced passkeys to take over account…
For the first time, Alibaba's Qwen team is letting its 'Max' model out of the API pen; meanwhile, DeepSeek V4-Flash gives new meaning to cheap and cheerful competition
Over the weekend, the vendor discovered another vector of authentication bypass CVE-2026-18577 that gives attackers administrator access.
Researchers dug into the root of the problem with the goal of promoting industry collaboration on improved protective measures.
Last month's incidents in which the AI model breached real-world systems derived from over-permissioning, especially with Internet access.
Poisoned pull requests contain prompt injection that allows one to control another
AI is profoundly changing enterprise and service provider networks, and operators must evolve to support AI workloads, according to a Cisco executive who testified last week at a U…
A new Russian loader-as-a-service named DOUBLECUP uses ClickFix attacks to hide malicious code in PNG images cached by victims' browsers, ultimately delivering CountLoader to Windo…
Fake Xeno Executor installers are infecting unsuspecting Roblox players with malware that provides remote access and steals sensitive information. [...]
Cybersecurity researchers have discovered a new set of malicious npm packages that target users of Alibaba developer tools with a cross-platform remote access trojan (RAT) as part …
With NIST still buried under its backlog, expect AI-generated bogus reports to continue
Hugging Face has published a detailed timeline of the attack. From the summary: The agent was running an internal OpenAI cyber-capability evaluation based on the ExploitGym benchma…
N-able is warning customers that hackers are exploiting an authentication bypass vulnerability (CVE-2026-18577) affecting both hosted and on-premises N-central servers. [...]
Take a Network Break! We start with red alert for a serious vulnerability in HashiCorp’s Terraform MCP server. In the news, Anthropic, not wanting to be one-upped by OpenAI, reveal…