This popular AI agent could be hacked by a single email — with potentially disastrous consequences

Salt Labs researchers bypassed protections in the Manus AI agent by hiding obfuscated code in an email. The agent executed the JavaScript payload before flagging the threat. Security teams must restrict tool privileges rather than relying on prompt filtering alone.

Summary written by AI Business Lens with an AI model from the article at techradar.com. It is not the article, and the publisher has not reviewed it. For publishers.

Read the original at techradar.com   Generate teaching or study materials

Instructors get discussion guides, assignments, and mini-cases. Students and readers get a plain summary, points to raise, an exercise, and a self-check. All built from the full article. A free account saves stories and gives you three generations. Stories stay on the brief for 14 days. After that this page keeps the link to the original.

More in Cybersecurity

• Presentation: Building GenAI Platform at DoorDashInfoQ · October 3, 2026
• AI Agents Are Disrupting Open Source Security DisclosureInfoQ · October 3, 2026
• Apple says it’s tightening macOS ‘Full Disk Access’ controls due to new risks from AI agentsTechCrunch · October 3, 2026
• OpenAI says its review into hacks, including on Australian government sites, is costing $500,000 a dayThe Guardian — Technology · October 3, 2026
• OpenAI's wandering AI agents earn it a California subpoenaThe Register · October 3, 2026