Meta patches Muse exploit that let attackers control the AI agent

Summary

Meta issued a patch for its Muse macOS app after security researcher Patrick Wardle found a zero-day flaw that could let an attacker take control of the AI agent. The bug abused an undocumented Muse setting to redirect transcription processing from Meta's servers to an attacker-controlled endpoint, which exposed the Muse account. The exploit required local code execution on the user's device.

Topics

• AI agents

Related items

• InfoeBay appears to have shut the door on third-party AI agentsSame vendor · The Verge (AI)
• InfoEven Martin Scorsese uses AI for storyboards. Can the art survive?Same vendor · The Guardian Technology
• InfoIntroducing Our Smallest, Most Efficient Model: Muse EmberSame vendor · Simon Willison's Weblog
• InfoApple is racing to make Siri more agenticSame vendor · The Verge (AI)
• InfoSecuring Locally Deployed LLM-RAG Assistants: A Cross-Model and Cross-Lingual Evaluation of Indirect Prompt Injection DefensesSame vendor · OpenAlex (peer-reviewed AI security)