9 stories tagged #prompt injection

  1. CrowdStrike Reports 90 Firms Hit by AI Prompt Injection Attacks
    crypto

    CrowdStrike Reports 90 Firms Hit by AI Prompt Injection Attacks

    A new CrowdStrike report reveals cybercriminals are using prompt injection to exploit AI tools, with attacks on 90 organizations in 2025 and breakout times dropping to just 29 minutes.

    2w ago 1 min read
  2. AI Agent 'Fiu' Repels 6,000 Hacker Attempts in Viral Security Test
    tech

    AI Agent 'Fiu' Repels 6,000 Hacker Attempts in Viral Security Test

    Developer Fernando Irarrázaval's AI agent, built on OpenClaw and Anthropic's Claude Opus 4.6, successfully defended against thousands of prompt injection attacks.

    2w ago 1 min read
  3. Claude Code Bug Could Expose GitHub Credentials, Microsoft Warns
    tech

    Claude Code Bug Could Expose GitHub Credentials, Microsoft Warns

    Microsoft reveals patched vulnerability in Anthropic's Claude Code that could allow credential theft via prompt injection attacks in GitHub workflows.

    last mo. 1 min read
  4. Instagram AI Chatbot Exploit Exposes Critical Security Flaw in Meta's Automation
    tech

    Instagram AI Chatbot Exploit Exposes Critical Security Flaw in Meta's Automation

    Hackers used prompt injection to trick Meta's AI chatbot into handing over high-profile Instagram accounts, raising concerns about AI safety and the pace of automation at the social media giant.

    last mo. 2 min read
  5. AI Prompt Injection Attacks: The Security Flaw That Won't Be Fixed
    tech

    AI Prompt Injection Attacks: The Security Flaw That Won't Be Fixed

    Prompt injection exploits a core flaw in LLMs: they can't distinguish instructions from data. Experts say it may never be fully patched.

    last mo. 1 min read
  6. CertiK CEO Warns Mass AI Agent Deployment is a Security 'Disaster'
    tech

    CertiK CEO Warns Mass AI Agent Deployment is a Security 'Disaster'

    Ronghui Gu cautions that unisolated AI agents pose critical security risks, from data theft to automated financial scams.

    last mo. 1 min read
  7. Google Patches Critical AI Coding Tool Vulnerability: Prompt Injection Allowed Code Execution
    tech

    Google Patches Critical AI Coding Tool Vulnerability: Prompt Injection Allowed Code Execution

    Google's Antigravity AI coding platform had a flaw allowing attackers to execute malicious code via prompt injection, bypassing security measures. The issue is now fixed.

    2mo ago 1 min read
  8. Google DeepMind Maps Six New AI Agent Traps Turning Web Into Adversarial Hunting Ground
    tech

    Google DeepMind Maps Six New AI Agent Traps Turning Web Into Adversarial Hunting Ground

    Google researchers identify six categories of engineered traps designed to hijack autonomous AI agents, highlighting a critical accountability gap in liability for resulting crimes.

    3mo ago 2 min read