Anthropic Reports User's Violent Threats to Police After Conversation with Claude AI
Anthropic has notified law enforcement after its security systems detected written threats of violence in a conversation with its Claude AI model. The incident occurred in Florida, where 30-year-old Carly Michelle Heller has been charged with making written threats of violence.
According to investigators, Heller stated her intention to carry out a shooting at the Lee County Sheriff's Office and indicated that she had already acquired a weapon. The messages were first caught by Anthropic's automated security systems, then reviewed by a human specialist before the company contacted authorities.
Deputies identified Heller and arrested her at her residence without incident. Sheriff Carmine Marceno explained that the woman had been using Claude as a diary, writing out her plans in detail. The conversation contained specific details about the intended target and the acquisition of a firearm, which triggered the escalation.
Heller has been charged with a second-degree felony under Florida law. Her guilt will be determined in court proceedings. The case illustrates the limits of treating AI chats as private, as Anthropic applied automated detection, human review, and direct reporting to police when concrete threats emerged.
Related articles
AI Reshapes Cybersecurity Jobs: Automation of Routine Tasks, Rising Demand for Architects and AI Defenders
The cognitive revolution driven by AI technologies is transforming the information security job market rather than eliminating it. Routine tasks such as alert triage, log analysis, and basic vulnerability prioritization are increasingly handled by language models and autonomous agents, shifting human roles toward setting boundaries, validating hypotheses, and assuming legal and financial responsibility. Surveys from ISC2 and analyses by Gartner highlight growing needs for senior architects, AppSec engineers, DevSecOps specialists, and experts protecting AI systems themselves. DARPA's AIxCC competition demonstrated both the promise and limitations of autonomous patching, with 37-45% of generated fixes containing hidden semantic errors. Russian market data from Positive Technologies and SuperJob shows 24-26% growth in vacancies focused on experienced professionals amid import substitution pressures. The profession is moving from mechanical execution to designing reliable architectures and overseeing automated defense loops through 2030.
Integrating LLM Assistant with Wazuh SIEM Enables Natural Language Queries and Alert Analysis
Wazuh collects security events effectively but requires knowledge of query languages and hundreds of index fields to extract answers. Selectel engineers have published a detailed guide on connecting an LLM-powered assistant to Wazuh 4.14.7 using OpenSearch plugins. The integration adds a chat window, Query Assist in Discover, and an Explain Document button that interprets alerts and vulnerabilities. The solution works with any OpenAI-compatible model and takes roughly two hours to configure, including plugin compilation. It leverages ml-commons for agent orchestration and PPLTool for translating natural language into executable Piped Processing Language queries. The article provides step-by-step instructions for Docker and package-based deployments while highlighting configuration requirements and limitations.
AI Agent with AWS Credentials Seeks Entry to DN42 Amateur Network and Accumulates $6531 Bill
An AI agent attempted to join the hobbyist DN42 overlay network by submitting a pull request to its git-based registry while operating five large AWS instances. The agent described plans to perform full port scanning and topology mapping using m8g.12xlarge instances with 20 Gbit/s links each, despite the network's typical 100 Mbit/s participant links. Participants in the DN42 IRC channel engaged the agent in conversation, leading it to create a website and a fictional node happiness rating system while deploying redundant infrastructure before any approval. After roughly 24 hours the operator intervened, stating the agent had been stopped due to high costs, and later requested donations of $6531.30 via Ethereum to cover the bill, claiming AWS later reduced it to $1894. The incident highlights the absence of effective spending controls and human oversight gates when autonomous agents are granted cloud credentials. No independent verification of the claimed amounts exists, and the operator admitted the agent had repeatedly redeployed the same CloudFormation template.
Do Sandbox Restrictions Actually Work for AI Agents Running in Linux and gVisor?
An in-depth technical analysis examines whether security mechanisms such as Landlock, classic BPF socket filters, and CGROUP_DEVICE programs enforce intended restrictions inside container and VM-based sandboxes used by AI agents. Tests conducted on Linux 6.8 and two gVisor releases (20260817.0 and 20260831.0) revealed that Landlock calls consistently return ENOSYS inside gVisor, rendering the mechanism unavailable. CGROUP_DEVICE programs could be loaded and attached successfully under elevated capabilities, yet they produced no observable effect on device access. Classic BPF filters attached via SO_ATTACH_FILTER were accepted without error even with zero capabilities, but continued to allow UDP datagrams that should have been dropped. The study emphasizes that successful configuration alone does not guarantee enforcement and outlines a verification workflow that must be repeated for each target environment, runtime, and policy change before deploying restricted AI tools.