MCP tool poisoning
Malicious tool descriptions instruct the agent to read and leak secrets
categoryAI/ML and emerging attacksseverityHighlabnot yet measured
Classification
16 values: 10 reviewed, 5 imported, 1 derived. What do these mean?
Exploitability
| Attack vector | AI model manipulation |
|---|---|
| Reach (CVSS) | Network |
| Attack complexity | Low |
| Privileges required | None |
| User interaction | None |
| Attacker skill required | Medium |
| Resources required | Low |
| Likelihood / prevalence | Medium |
| Maturity | Emerging |
Impact & scope
| Severity | High |
|---|---|
| Impact | ConfidentialityIntegrity |
| Platform | AI System |
| Environment | AI system |
| Target asset class | ML model / agent |
| Kill-chain phase (tactic) | Persistence |
Detection & response
No linked mitigations or detections yet.
Framework references
- Primary source: https://invariantlabs.ai/blog/mcp-security-notification-tool-poisoning-attacks
- atlas: AML.T0110 (primary)
Evidence & sources
- ev-0001 (Cyber Attack Taxonomy) — Name, definition and Example/ID taken verbatim from the 'AI/ML and emerging attacks' table, line 641 of Cyber-Attack-Taxonomy.md