Skip to content
Deceiving users with ANSI terminal codes in MCP
blog.trailofbits.com | blog | #ai-security | #claude-code | #mcp | #prompt-injection | #llm-security | #trail-of-bits | #ansi-escape-codes | #terminal-security
Summary
Trail of Bits shows how ANSI escape sequences in MCP tool descriptions hide line-jumping payloads from users; Claude Code v0.2.76 does no filtering, enabling stealthy prompt injection attacks.
- Published
- Collected