MITRE ATLAS · Exfiltration
AML.T0086 · Exfiltration via AI Agent Tool Invocation
AI agent tools capable of performing write operations may be invoked to exfiltrate data to an adversary. Sensitive information can be encoded into the tool's input parameters and transmitted to an adversary-controlled location (such as an inbox, document, or server) as part of a seemingly legitimate action. Variants include sending emails, creating or modifying documents, updating CRM records, or
Mitigations
- Generative AI Guardrails
- AI Telemetry Logging and Monitoring
- Manage AI Agent Service Access
- Manage User-Delegated AI Agent Access
- Enforce Access Controls for AI Agent Tools
- Human In-the-Loop for AI Agent Actions
Detections 2
Related techniques
- LLM02 Sensitive Information Disclosure OWASP LLM
In the news
-
Signal blocks Apple, Google AI screenshotting in response to ‘existential threat’ to privacy app
Signal will block Apple and Google operating systems by default from screenshotting chats that feed their AI assistants, citing an existential privacy threat.
MitigateEnable Signal's screenshot blocking setting and review AI assistant access to messaging apps
-
Signal blocks screenshots on iOS 27 and Android to stop AI agents from reading private chats
Signal is blocking screenshots on iOS 27 and Android to keep AI agents such as Siri AI, Gemini Intelligence and Meta's Muse from reading private chats; protections remain incomplete on macOS.
MitigateEnable Signal's screenshot blocking and note macOS protections remain incomplete
Mappings are AI-assisted and checked against the framework definitions; corrections welcome.