tool-poisoning

2 posts.

• 
  MCP security labs: path bypasses and poisoned tool responsesDay 7 / 100 · AI cybersecurity

  Two MCP labs showed different failures at the same boundary: a filesystem server trusted a string prefix, while a facts server poisoned the agent's next tool call.

• 
  MCP security: when prompt injection gets a toolDay 5 / 100 · AI cybersecurity

  MCP makes it easier for AI systems to use external tools. It also connects model behaviour to permissions, private data, and real actions.