By Vero SecurityBuilt and funded by Vero Security, the AI Security Engineering platform.Read the charter

Output filtering and data loss prevention

Agent output is untrusted input to whatever consumes it next: a browser, a shell, a ticket or another agent. Filter for secrets and personal data, refuse to render remote images or links built from model output, and encode output for its destination. Many real exfiltration bugs were markdown images that leaked data through a URL.

Read in this order

  1. OfficialLLM05:2025 Improper Output Handling (OWASP GenAI Security Project)Start here: why model output must be treated as untrusted input.
  2. ArticleBing Chat: Data Exfiltration Exploit Explained (Embrace The Red)A real markdown image exfiltration, with the fix that closed it.
  3. Open sourcePresidio: data protection and de-identification SDKA tool for detecting and masking personal data in agent output.

Save your progress

We email you a sign-in link. No password.

By signing in you agree to the terms. The privacy policy explains how we use your details.

Join the AI security engineering community

Free. Roadmap updates, chapters near you, and first word when credentials open.

We’ll email you community updates. Unsubscribe anytime. By sending this you agree to the terms. The privacy policy explains how we use your details.