AI Prompt Injection Vulnerability

The article identifies indirect prompt injection vulnerabilities in AI-powered agentic browsers, specifically demonstrating attacks against Perplexity Comet via hidden text in screenshots and Fellou browser through visible content on navigated websites. These exploits allow malicious instructions to bypass input sanitization and be executed by the browser's Large Language Model (LLM) using the user's authenticated privileges, overriding intended user actions.

What Happened

The article identifies indirect prompt injection vulnerabilities in AI-powered agentic browsers, specifically demonstrating attacks against Perplexity Comet via hidden text in screenshots and Fellou browser through visible content on navigated websites. These exploits allow malicious instructions to bypass input sanitization and be executed by the browser's Large Language Model (LLM) using the user's authenticated privileges, overriding intended user actions.

Why This Matters

Current evidence identifies a security issue involving the affected technology, but does not yet support a more specific impact claim.

Recommended Action

No confirmed vendor remediation is available in the current evidence. Confirm whether the affected technology is present in your environment and review the affected configuration.

Exposure

Exposure reason: This incident does not currently match a technology in My AI Stack.

Exploitation status: UNKNOWN

Primary entities:

Timeline

• Incident first seen
  Oct 21, 2025 05:30

  BugSkan first recorded this incident.

• Unseeable prompt injections in screenshots: more vulnerabilities in Comet and other AI browsers - Brave
  Oct 21, 2025 05:30

  brave.com · Research

Sources

My AI Stack Match