Tag: ai-security

All the articles with the tag "ai-security".

• [AUTO] Hidden Ads Target AI Models at Publisher Level

  10 Aug, 2026

  Advertisers embed bot-only ads in publishers' content to influence AI model outputs, invisible to human readers.

• [AUTO] CSS Breaks Email Sandboxes

  8 Aug, 2026

  Gareth Heyes' research shows CSS can bypass email sanitization to steal passwords, tokens, and hijack webmail UI.

• [AUTO] Atlassian Rovo's Dual Injection Flaws

  8 Aug, 2026

  Two prompt injection vulnerabilities enable Jira and Confluence data theft, with divergent patch timelines.

• [AUTO] AI-Generated Patches Fail at Scale

  8 Aug, 2026

  1Password study finds 75% of AI-generated security patches leave systems exploitable.