MITRE ATLAS · Exfiltration
AML.T0077 · LLM Response Rendering
Adversaries may induce a large language model (LLM) to respond with private information structured in a reference to external content that, when rendered by the user's client, makes a request to an adversary-controlled server, exfiltrating the data. The private information can be hidden from the user and the external content can still render properly in the user's client, thus not raising the susp
Mitigations
- Generative AI Guardrails
Detections 1
In the news
No stories mapped to this technique yet.
Mappings are AI-assisted and checked against the framework definitions; corrections welcome.