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

Exfiltration channels to close

Attackers exfiltrate through anything the agent can reach: allowlisted commands that make DNS lookups, web fetch tools, rendered links, and MCP servers with write access to public places. Each channel needs its own control, because a network proxy alone does not see tool calls. Test your setup with known exfiltration techniques before calling it safe.

Read in this order

  1. ArticleThe lethal trifecta for AI agents (Simon Willison)Start here: why any outbound channel plus private data is enough.
  2. ArticleGitHub MCP exploited: accessing private repositories via MCP (Invariant Labs)A real attack that leaked private repos through an MCP server.
  3. ArticleClaude Code: Data exfiltration with DNS, CVE-2025-55284 (Embrace The Red)Shows a quiet DNS channel you can replay against your own setup.

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.