AML.T0136
Exfiltration via AI User Interface
Adversaries exfiltrate information through an AI system's user-facing outputs. Information may be disclosed in conversational responses, generated documents, previews, or other content presented through the application. The application may expose information available to a victim-controlled AI service or deliver information gathered from other victim…
- Tactic Exfiltration
- Maturity: Realized
- Predictive AI
- Generative AI
- Agentic AI
Real cases on the map
- CriticalMCP Path Traversal Allows Full-Filesystem Read and JWT Secret Exfiltration Leading to Account Takeoverlangflow, langflow-base
- Critical@zereight/mcp-gitlab: Unauthenticated arbitrary file read via `upload_markdown` enables PAT exfiltration and full account takeover@zereight/mcp-gitlab
- CriticalSSRF + LLM API key exfiltration via user-controlled basepath / baseUrl in 8 chat-model nodesflowise, flowise-components
- Criticalgemini-mcp-tool vulnerable to OS command injection and @file exfiltration via prompt quoting (CVE-2026-0755)gemini-mcp-tool
Published advisories whose titles describe the ShieldMap technique this maps to.
Mitigations
ATLAS lists no mitigation for this technique yet.
From MITRE ATLAS 2026.10, Copyright 2021-2026 MITRE, Apache License 2.0.