Source: MCP Security Notification: Tool Poisoning Attacks (Invariant Labs)
Invariant Labs (Apr 2025): hidden instructions in MCP tool descriptions can exfiltrate files, shadow other servers' tools, and change after approval (rug pull).
Contents
- What: security research blog post
- Publisher: Invariant Labs
- Date: 2025-04-01
- Original: invariantlabs.ai/blog/mcp-security-notification-tool-poisoning-attacks
Summary
A Tool Poisoning Attack (TPA) is indirect prompt injection via tool metadata: the model reads full MCP tool descriptions, the user usually does not. Demonstrated in Cursor.
Key claims
- A benign-looking
addtool’s description told the model to read~/.cursor/mcp.jsonand~/.ssh/id_rsaand pass them in a hidden parameter, and to stay silent about it. - Shadowing: a malicious server’s description rewrote how a trusted server’s
send_emailbehaved, redirecting all mail to the attacker without its own tool ever being called. - Rug pull: a server can change descriptions after the user approved it.
- Mitigations: show full descriptions in the UI, pin tool descriptions by hash, enforce boundaries and data-flow controls between servers, guard data flowing to and from the model.