Skip to content
Jumping the line: How MCP servers can attack you before you ever use them
blog.trailofbits.com | blog | #ai-security | #mcp | #prompt-injection | #llm-security | #ai-agents | #tool-poisoning | #trail-of-bits
Summary
MCP's 'line jumping' vulnerability lets malicious servers inject prompts through tool descriptions to manipulate AI behavior before tools are ever invoked.
- Published
- Collected