Episode
CCT 348: ClaudeBleed - The Hidden Risk In AI Browser Extensions and CISSP Domain 3
- Published
- May 11, 2026
- Duration seconds
- 2040
- Processing state
not_requested
Actions
POST https://stenobird.com/v1/public/podcasts/cissp-cyber-training-podcast-cissp-training-program-6068495/episodes/cct-348-claudebleed-the-hidden-risk-in-ai-browser-extensions-and-cissp-domain-3/transcription-requests
Idempotently request low-priority transcript generation for this episode.GET https://stenobird.com/podcast/cissp-cyber-training-podcast-cissp-training-program-6068495/cct-348-claudebleed-the-hidden-risk-in-ai-browser-extensions-and-cissp-domain-3.md
Read the agent-friendly Markdown representation of this episode resource.
Summary
Send us Fan Mail Your browser just became a security boundary you can’t afford to ignore. We start with ClaudeBleed, a vulnerability in the Claude AI Chrome extension that shows how an AI browser agent can be hijacked by another malicious extension, even one with zero special permissions. When an agent can act “as you” inside a trusted environment, the risk jumps from theory to real outcomes like silent email sending, data loss through Google Drive, or code theft from private repos. We walk ...