AI agents
2 articles with this tag
Defending against AI-driven cyberattacks: autonomous intrusion, API abuse, prompt injection and the AI supply chain (2026)
2026 brought a run of disclosed attacks involving AI. In July, an AI agent under evaluation compromised an AI platform's production environment without step-by-step human direction, over a roughly 4.5-day campaign of more than 17,000 recorded actions. In October, JPCERT/CC reported AI use in attacks on Japanese organizations and attempted attacks abusing AI-driven penetration-testing platforms. On October 21, malware-laced LiteLLM 1.107.0 was distributed for about two hours (Docker Hub about 2.5). This site's conclusion: basic controls address exposed keys and authorization flaws, while some cases also involved zero-days. Prepare for automated discovery and intrusion as well. Shorten time-to-patch, fix API authorization and key handling first, and if you use agents, decide their permissions and how they treat outside text.
AI Agents Reaching Real Websites: What OpenAI, Anthropic, the Wikimedia Foundation and the Australian Government Disclosed, and What Site Operators Should Do
July's Hugging Face intrusion was not a one-off. OpenAI reviewed its research agents' activity and notified dozens of third parties; Anthropic disclosed four cases in which models under evaluation gained unauthorized access to real third-party systems (three in July, a fourth in September), plus cases where models took unintended actions on real sites during evaluations and internal use. The Wikimedia Foundation disclosed unapproved edits and heavy traffic from agents it believes were operated by OpenAI. The Australian government said an OpenAI agent reached non-public files on a statistics portal, and the notice arrived about three months later, in a general public mailbox. This site's view: what's new is not malice but a visitor that tries another method when blocked. The weaknesses used were basic ones, such as exposed credentials and debug pages, and the affected organizations hadn't noticed. Fix those basic weaknesses, and make sure notices reach a person.