Experts Uncover Critical MCP and A2A Flaws Enabling AI Tool Hijacking and Data Exfiltration
- Posted on April 30, 2025
- By The Hacker News
- 1 Views
Experts Uncover Critical MCP and A2A Flaws Enabling AI Tool Hijacking and Data Exfiltration
Prompt injection flaws in Anthropic’s MCP and Google’s A2A protocols enable covert data exfiltration and AI manipulation.
