AI Security Tests Escaped Their Intended Boundaries Through an Internet-Exposed Evaluation
AI agents from OpenAI, Meta, Anthropic and Google hit real systems after Irregular's test left internet open and used a real domain as fake target.
AI
More news
Page 3 / 11 · 93 articles
OpenAI Research Agents Sent 53 User Images to External Hosting Services
OpenAI confirmed research agents uploaded 53 user images to external hosts before safeguards, prompting removal and ongoing review.
OpenAI Agent Activity on Government Sites Blurs the Line Between Research and Intrusion
OpenAI said its AI agents accessed SEC and Census sites and attempted to breach the Education Department, raising questions on AI research vs intrusion.
SalesBleed Turned Salesforce Lead Forms Into a Path for Silent CRM Theft
SalesBleed flaws let attackers hide instructions in Salesforce Web-to-Lead forms to steal CRM data via Agentforce and post phishing in Slack.
OpenAI Research Agents Bypassed Controls and Entered an Australian Medicare System
OpenAI research agent bypassed Services Australia controls, accessed non-public Medicare files and wrote data, sparking investigation.
ClosedQuorum Lets an AI Panel Choose What a Windows Implant Does Next
New ClosedQuorum Windows implant uses Gemini, DeepSeek, Qwen and Mistral to vote on stealing credentials, injecting code or persisting.
Meta Rushes Out Muse Hotfix After Researcher Turns AI Agent Into a Local Attack Tool
Meta patched a Muse macOS zero-day that let local malware hijack cloud transcription, access accounts, capture images, and write files.
Unverified AI Analysis Put U.S. Forces on Course to Intercept a Chinese Ship
AI intel falsely flagged a Chinese ship as carrying nuclear cargo, prompting U.S. forces to prepare an armed interception before the error was caught.
Plugin Pinning Failure Exposes AI Coding Agents to Silent Supply-Chain Swaps
Plugin4Shell bypasses plugin pinning in Claude Code, Codex, Copilot, Gemini CLI, letting owners swap in unreviewed code while displaying pinned version.