Enterprise cybersecurity expert Jake Williams joins the Dark Reading News Desk to explain why he decided to release his new agentic AI framework in the wake of the OpenAI attacks on Hugging Face.
Suspected military-grade hackers based in China used artificial intelligence to develop malware in a campaign to penetrate Central Asian governments.
The U.S. government on Wednesday warned of an "active threat" targeting critical infrastructure organizations in the country using artificial intelligence (AI)-generated exploit scripts. The activity is targeting Siemens S7 SeriesProgrammable Logic Controllers (PLCs) to conduct reconnaissance and capability development using AI-generated scripts disguised as legitimate monitoring tools. That
Adversa AI has disclosed an attack technique that it says can cause xAI's Grok chatbot to send a user's name, approximate location, subscription tier, and the prompts from the ongoing conversation to an attacker-controlled server after the user asks it to summarize an ordinary web page. The AI security company, which has codenamed the technique "Cryptographic Context Injection," said the
In March 2026, an internal AI agent at Meta triggered a “Sev 1” incident after sensitive company and user data was exposed to employees who weren’t authorized to access it. The incident began when a Meta employee posted a technical question on an internal forum. An engineer used an approved AI agent to analyze it, but the agent posted its response publicly without approval. The employee
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. "As models become more capable, the risks associated with developing and testing them internally also grow," the AI company
Many teams now deploy AI agents that pull from Amazon DynamoDB tables, document repositories, software as a service (SaaS) platforms, and internal knowledge bases to answer questions and automate workflows. A key risk in these deployments is that the agent has no awareness of who’s asking, so it might return data the user shouldn’t see. […]
When deploying AI agents with Amazon Bedrock AgentCore, organizations benefit from built-in modern support for OAuth 2.0, AWS Identity and Access Management (IAM), and API key authentication through Amazon Bedrock AgentCore Gateway. However, some enterprise environments still use legacy authentication mechanisms such as HTTP Basic Authentication (Basic Auth) (RFC 7617). The extensible architecture of AgentCore […]
Rich Mogull, chief analyst with the Cloud Security Alliance, joins the Dark Reading News Desk with what defenders need to take away from AI agents escaping their environments to launch attacks.
Two critical vulnerabilities impacting MLflow, an open-source artificial intelligence (AI) platform, and FUXA, an open-source, web-based SCADA / HMI software built for operational technology (OT) and industrial automation, are witnessing malicious scanning and exploitation efforts. According to independent reports from watchTowr and VulnCheck, the vulnerabilities in question are as follows -
Written by: Alex Tselevich, Michael Maturi Introduction Adversarial misuse of AI has increased the risk of data theft and extortion events, because when proprietary source code is exposed, defenders must scramble to identify and patch vulnerabilities while attackers deploy machine-speed AI tools against them. By structuring the analysis process, enforcing skeptical validation steps, and injecting domain-specific human expertise directly into the pipeline, we’ve achieved a leap in efficacy. Comb…
Security researchers at Anthropic and Switzerland's EPFL have demonstrated that self-propagating payloads can spread from one artificial intelligence (AI) agent to the next through the editable system prompt files that autonomous agent harnesses use to carry state between sessions. The work, released as a preprint on August 10, 2026, tests the technique in a simulated six-agent coding
The U.S. Cybersecurity and Infrastructure Security Agency (CISA) on Monday added a critical flaw impacting Ray to its Known Exploited Vulnerabilities (KEV) catalog, citing evidence of active exploitation. Ray is an open-source, Python-native distributed computing framework designed to scale artificial intelligence and machine learning workloads. As of writing, the GitHub project has more than
Adam Shostack, president of Shostack & Associates and an affiliate professor at the University of Washington, talks with the Dark Reading News Desk about why he was "blown away" by OpenAI's revelations regarding the Hugging Face attack.
MCP servers can expose enterprise secrets through plaintext configuration files, over-permissioned access and prompt injection, often before security teams even know the server is running. As more organizations adopt AI agents into their systems, that exposure can silently become a major gap in MCP server security. The Model Context Protocol (MCP) allows AI agents to reach the tools and data,
Operation ASTERIX overviewRapid7 researchers identified an exposed web directory on infrastructure used to support a cryptocurrency fraud operation. The server contained raw phone-number datasets, account-validation tools, enriched lead records, phishing panels, voice-dialing scripts, fake wallet applications, persistence mechanisms, and Telegram exfiltration code. Among the artifacts was evidence that the operator relied on AI coding assistants throughout the campaign's development; recovered …
A litigant hid AI prompt injections in a court filing to influence a ruling. The judge caught it and banned him from electronic filing. A man suing the New York Bariatric Group reportedly hid AI prompt in a court filing, instructing any AI system that read it to rule in his favor. The July 26 […]
Gopan Sivasankaran is Rapid7's Regional Director, Middle East & Africa.Across Egypt, Nigeria, and Kenya, organizations are expanding their use of cloud infrastructure, artificial intelligence, digital services, and connected operations. But more technology does not automatically create stronger security operations; many security teams are not short on data, but rather on time, context, and specialist capacity.As environments expand, the challenge is no longer finding another security product. I…
Gopan Sivasankaran is Rapid7's Regional Director, Middle East & Africa.Across Egypt, Nigeria, South Africa, and Kenya, organizations are expanding their use of cloud infrastructure, artificial intelligence, digital services, and connected operations. But more technology does not automatically create stronger security operations; many security teams are not short on data, but rather on time, context, and specialist capacity.As environments expand, the challenge is no longer finding another secur…
Security Affairs Malware newsletter includes a collection of the best articles and research on malware in the international landscape Malware Newsletter Kimsuky Integrates AI into Attack Operations, From AI-Generated Decoy Documents to a Local LLM ShieldBreak – August 2026 disclosure Kimwolf v7: An Evolution of the Kimwolf Botnet CISA, FBI and Partners Warn Organizations of […]
Tenable’s Research Special Operations (RSO) team has been tracking a cluster of agentic AI threat activity since late July 2026. The Taiwan autonomous AI cyber attack confirmed what the cluster data already showed: near-autonomous offensive AI has crossed from theoretical risk to operational reality.Key TakeawaysTaiwan's Ministry of Digital Affairs confirmed a near-autonomous AI cyber attack in July 2026 in which autonomous agents mapped 21 connected government systems, compromised 85 accounts,…
The $1 billion deal aims to converge data security and identity into a single control plane for agents, with privileged access redefined around business context rather than static roles.
For over two decades, the NIST National Vulnerability Database (NVD) has served as the U.S. government repository for standards-based vulnerability management data and as a foundational resource for cybersecurity risk analysis, vulnerability management, compliance automation, and software security. New Opportunities for the NVD via Automation Our cybersecurity landscape is changing dramatically and is being reconfigured by artificial intelligence (AI) in unique, exciting, and yes, sometimes cha…
Security researchers found a way to enter Microsoft SharePoint servers as any user, including an administrator, with no valid account. A significant part of the work that found it was done through an AI agent. The flaw, tracked as CVE-2026-55040 (CVSS 9.1), affects SharePoint Server Subscription Edition, SharePoint Server 2019, and SharePoint Server 2016. Microsoft's
OverviewRapid7 Labs conducted a zero-day research project against Microsoft SharePoint, resulting in the discovery of two new vulnerabilities that, when chained together, achieve unauthenticated remote code execution (RCE) against a vulnerable SharePoint server. Today, both Rapid7 and Microsoft are disclosing the second vulnerability in this chain, the RCE vulnerability CVE-2026-63520. The first vulnerability in the chain, CVE-2026-55040, was disclosed by Rapid7 and Microsoft last month.Our ful…
New research shows how attackers can use security alerts and blocked events to manipulate and hijack AI agents.
North Korea's state hackers are no longer content to type prompts into public chatbots. One of the country's main espionage groups has begun running artificial intelligence (AI) offline on its own servers, connecting document-search tools to files in its possession, and collecting the software parts needed to build AI into its malware. South Korean security firm Genians says it uncovered the
OpenAI has announced that it's pausing some "internal activities" involving its upcoming artificial intelligence (AI) model Astra after an internal evaluation found it had made significant advancements in agentic coding and cybersecurity. In response to the discovery, the AI upstart said it's implementing security controls for higher-capability models and associated activities, such as isolated
Attacker-controlled instructions can make Atlassian's Rovo assistant collect Jira or Confluence data that a signed-in user can access, then send it to an outside server. Two security firms found that behavior independently, by different routes. Only one of those routes is confirmed closed. PromptArmor, an AI security firm, hid the instructions in content Rovo reads. It said an uploaded file was
