ANSI escape injection in MCP servers: Hidden from humans, visible to AI

 (brightsec.com)

14 points | by xgpyc2qp 2 days ago

5 comments

  • illliillll 22 minutes ago
    Every year is apparently a good year for developers to figure out how terminals have worked for decades?
  • qwertox 32 minutes ago
    > DAST is the natural way to catch this class of flaw. The Bright scanner...
  • hahahaa 18 minutes ago
    So cat -v is no longer harmful?
  • xgpyc2qp 2 days ago
    [dead]
  • doodlebyte 56 minutes ago
    This is a really interesting class of failure. It feels like we're going to see more cases where the "human view" and the "LLM view" of the same data diverge. Have you run into similar issues outside of MCP as well, or is this mostly specific to terminal-based tool interactions?
    [-]