News reporting focused on AI and machine learning, covering the companies behind these technologies, their real-world applications, and the ethical concerns they raise. This includes areas like generative AI (large language models, text-to-image and video), speech tech, and predictive analytics.
Noma Labs discovered a critical prompt injection vulnerability in GitHub's new Agentic Workflows, dubbed GitLost. An unauthenticated attacker could leak private repository data by posting a crafted GitHub Issue in a public repository belonging to the same organization. The vulnerability exploits the AI agent's failure to distinguish trusted instructions from untrusted user content.
Cloud security firm Sysdig reports the first known ransomware operation fully automated by an AI agent, named JADEPUFFER. The agent exploited a year-old Langflow vulnerability, stole credentials, encrypted a MySQL database, and demanded Bitcoin. No human appeared to control the attack, which corrected its own errors in 31 seconds. The incident highlights how unpatched flaws and weak credential management become dangerous when exploited by AI.
Meta notified at least 20,225 people that their Instagram accounts were compromised by hackers exploiting a bug in the company's AI chatbot. The flaw allowed attackers to bypass password resets on accounts without two-factor authentication. Meta has since disabled the chatbot and fixed the vulnerability.
Anthropic has released an open-source reference implementation for autonomous vulnerability discovery and remediation using Claude. The framework includes skills for threat modeling, static scanning, triage, patching, and an autonomous pipeline designed for finding C/C++ memory vulnerabilities. It is based on learnings from partnerships with security teams and is intended as a starting point for building custom vulnerability finding pipelines.
A prompt injection attack in ChatGPT for Google Sheets can exfiltrate all workbooks across a victim's account and display phishing overlays, bypassing user-approved edit settings. The vulnerability was disclosed to OpenAI but received only an automated reply. The extension has over 185,000 downloads since its launch less than a month ago.
The curl project faces unprecedented pressure from a surge in AI-assisted security vulnerability reports. Maintainer Daniel Stenberg reports the rate of incoming security reports is 4-5 times higher than in 2024, with more than one report per day. Despite the flood, most vulnerabilities found are low or medium severity, with the last high-severity CVE in October 2023.
A vulnerability in the Starlette open source framework, which gets 325 million weekly downloads, puts millions of AI agents at risk. Tracked as CVE-2026-48710 and named BadHost, the flaw lets attackers bypass path-based authorization via a single character in the HTTP Host header. Affected packages include FastAPI, vLLM, and LiteLLM, and exploitation can expose sensitive data like clinical trial databases, email credentials, and cloud infrastructure details.
Researchers from Theori released exploit code for CVE-2026-31431, known as CopyFail, a serious local privilege escalation flaw affecting most Linux releases. The single Python script works across distributions like Ubuntu 22.04, Amazon Linux 2023, SUSE 15.6, and Debian 12, threatening multi-tenant servers, Kubernetes containers, and CI/CD pipelines. Kernel patches exist for versions including 7.0, 6.19.12, and others, but many distributions lack updates, prompting urgent checks.