Security Update News
Update Information
| Title |
How Microsoft defends against indirect prompt injection attacks |
| Update ID |
MSRC:601D8198724874CAB6530A9335CFA031 |
| Type |
msrc |
| Published |
2025-07-29T07:00:00 |
| Last Updated |
2025-07-29T07:00:00 |
Security Impact
AI Analysis
| AI Description |
An attacker could provide specially crafted data that a large language model (LLM) misinterprets as instructions, posing a risk to systems leveraging LLMs to process untrusted data. |
| AI Severity |
High |
| AI Vendor |
Microsoft |
| AI Product |
Large Language Models (LLMs) |
Update Details
Summary The growing adoption of large language models (LLMs) in enterprise workflows has introduced a new class of adversarial techniques: indirect prompt injection. Indirect prompt injection can be used against systems that leverage large language models (LLMs) to process untrusted data. Fundamentally, the risk is that an attacker could provide specially crafted data that the LLM misinterprets as instructions.
View Advisory Details
