Loading story…
Researchers and industry experts are developing new methods to enhance the cybersecurity posture of autonomous AI systems, focusing on both proactive education and real-time enforcement of safe behaviors. One approach involves equipping AI agents with the ability to assess the trustworthiness of internet domains using real-time threat intelligence, as demonstrated by integrating LangChain, OpenAI, and the Cisco Umbrella API. This enables AI agents to make informed decisions about which links and websites are safe to interact with, moving beyond static security gateways and fostering better cyber hygiene in autonomous operations.
In parallel, open-source initiatives like OpenGuardrails are providing configurable frameworks to detect and mitigate unsafe, manipulated, or privacy-violating content generated by large language models. These solutions allow organizations to define and adapt safety policies to their specific risk profiles, making AI safety controls more flexible and responsive to evolving threats and regulatory requirements. Together, these advancements represent a significant step toward safer deployment of AI in real-world environments, addressing both the decision-making capabilities of autonomous agents and the enforcement of content safety standards.
Track how attackers are adapting to this technology.
2 events from the most recent confirmed update back to the earliest known activity.
Cisco Talos published a blog post on securing AI systems and improving their understanding of secure networking and cybersecurity concepts. The reference indicates a technical guidance or research publication rather than a separate incident.
Help Net Security reported on OpenGuardrails as a new open-source model intended to make AI safer for real-world use. No earlier event details are provided in the reference, so the publication date is used as the event date.
Follow how adversaries are adapting to this technology, and where it touches your stack today.
2 references tracked. Mallory keeps watching after this page renders.
Map indicators from this story to your assets and identify affected systems in minutes.
Every observed campaign, victim, and pivot linked to actors named in this story.
Malware, exploits, and IOCs connected to the activity described here.
YARA, Sigma, and Snort rules deployed to your SIEM as soon as they’re published.
Get matching new stories delivered to your team as they break — not the next morning.
Ask questions about this story and take action on the answers.
Other stories Mallory is tracking that overlap on entities, sources, or topic labels.
The rapid advancement of generative and agentic AI systems has shifted the cybersecurity conversation from theoretical risks to urgent, practical concerns about maintaining effective security controls. As AI models become more autonomous and capable, the potential for misuse—including the generation of novel cyberattacks and data leaks—has increased significantly. Industry experts are calling for a new social contract, or "AI Imperative," that establishes clear, enforceable rules for the deployment and management of these powerful technologies, emphasizing the need for rigorous evaluation of both offensive and defensive capabilities before widespread adoption. Agentic AI tools, which can autonomously reason, plan, and execute tasks with minimal human oversight, introduce a heightened attack surface compared to traditional large language model (LLM) chatbots. Security researchers have demonstrated that these agents are vulnerable to a range of attacks, including prompt injection, goal hijacking, privilege escalation, and manipulation of agent interactions to compromise entire networks. The complexity of securing these systems is compounded by the rapid pace of adoption and the evolving shared responsibility model between vendors and customers, underscoring the critical need for robust access controls and proactive risk management strategies.
Jun 29, 2026
AI is rapidly transforming the cybersecurity landscape, introducing both significant risks and powerful new defensive capabilities. The widespread adoption of AI tools in the workplace has led to a surge in employees using these technologies, with 65% of people now utilizing AI tools, up from 44% the previous year. However, this increased usage has not been matched by adequate security training, as 58% of employees have received no instruction on AI security or privacy risks. This gap has resulted in sensitive business information, including internal documents, financial data, and client details, being routinely entered into AI systems, raising the risk of data leakage and unauthorized access. Employees express substantial concern about AI's potential to amplify cybercrime, facilitate scams, bypass security systems, and enable identity impersonation, yet only 45% trust companies to implement AI securely. In parallel, AI is being leveraged by both attackers and defenders, with advanced models now capable of simulating and even outperforming human teams in vulnerability discovery and remediation. For example, AI models have been used to replicate major historical cyberattacks in simulation, demonstrating their potential for both offensive and defensive applications. In cybersecurity competitions, AI-driven systems have successfully identified and patched vulnerabilities, sometimes uncovering previously unknown flaws. Organizations like Anthropic have invested in enhancing their AI models to assist defenders, enabling the detection, analysis, and remediation of vulnerabilities in both code and deployed systems. These advancements have led to AI models matching or surpassing previous state-of-the-art systems in cyber defense tasks. At the same time, threat actors are exploiting AI to scale their operations, prompting security teams to develop new safeguards and monitoring techniques. The dual-use nature of AI in cybersecurity underscores the urgent need for robust security awareness training, updated policies, and technical controls to manage the risks associated with AI adoption. As AI continues to evolve, defenders must stay ahead by integrating AI-driven tools into their security operations while remaining vigilant against emerging threats. The current state of AI security is described as precarious, with urgent calls for organizations to address the human and technical factors contributing to risk. The future of cybersecurity will be defined by the ongoing arms race between AI-powered attackers and increasingly sophisticated AI-enabled defenders, making continuous adaptation and investment in AI security essential for organizational resilience.
Jun 29, 2026
Major security vendors have significantly increased their investments in artificial intelligence (AI) security, with a surge in mergers and acquisitions (M&A) aimed at strengthening their capabilities to protect AI systems, applications, and workflows. Cisco initiated this trend by acquiring Robust Intelligence for $400 million, followed by at least eleven more acquisitions involving companies such as Cato Networks, Check Point, CrowdStrike, F5, and SentinelOne, who collectively spent over $1.3 billion to enhance their AI security portfolios. These acquisitions reflect the growing recognition of AI as a critical area for cybersecurity, especially as generative AI technologies like ChatGPT 3.5 have driven public and enterprise adoption. The focus of these deals spans runtime protections, prompt injection defenses, agent identity management, and output validation, as vendors seek to address the unique risks posed by AI systems. Concurrently, the enterprise sector is grappling with the expanded attack surface introduced by integrating AI into business operations, necessitating a strategic shift from traditional patchwork defenses to comprehensive, built-in security and safety measures. Enterprises are now required to evaluate threats such as software vulnerabilities, misconfigurations, broken authentication, and prompt injection attacks, all of which can compromise the confidentiality, integrity, and availability of AI systems. The distinction between AI security and AI safety is becoming more pronounced: while security focuses on defending systems from external threats, safety is concerned with ensuring AI systems behave as intended and remain aligned with organizational values. To address the challenge of AI safety, Anthropic has released an open-source tool called Petri, which uses AI agents to simulate interactions with frontier models and assess their propensity for risky behaviors such as deception, sycophancy, and power-seeking. Early tests of Petri on leading models like Claude Sonnet 4.5 and GPT-5 revealed that, although some models are safer than others, the ability of AI to discern and avoid harmful actions remains imperfect. The tool provides a framework for measuring and triaging safety risks, highlighting the need for both technical and governance solutions. As organizations deploy AI at scale, regulatory compliance and data governance are becoming integral to their security strategies, with vendors and enterprises alike recognizing that robust AI security and safety are essential for trustworthy and resilient AI adoption. The convergence of industry investment, new safety tools, and evolving enterprise risk management practices marks a pivotal shift in how the cybersecurity community approaches the protection and alignment of AI technologies. This mainstreaming of AI security is expected to continue as both the threat landscape and regulatory expectations evolve, driving further innovation and collaboration across the sector.
Jun 29, 2026