Agentic applications are programs that leverage AI agents — software designed to autonomously collect data and take actions toward specific objectives — to drive their functionality. As AI agents are becoming more widely adopted in real-world applications, understanding their security implications is critical.
This article investigates ways attackers can target agentic applications, presenting nine concrete attack scenarios that result in outcomes such as information leakage, credential theft, tool exploitation and remote code execution. To assess how widely applicable these risks are, we implemented two functionally identical applications using different open-source agent frameworks — CrewAI and AutoGen — and executed the same attacks on both. Palo Alto findings show that most vulnerabilities and attack vectors are largely framework-agnostic, arising from insecure design patterns, misconfigurations and unsafe tool integrations, rather than flaws in the frameworks themselves.
Read more…
Source: Palo Alto Unit 42
Sign up for our Newsletter
The latest news and insights delivered right to your inbox.
Related:
- NSA Advocates Data Sharing Framework
June 23, 2017
The economics of cybersecurity are skewed in favor of attackers, who invest once and can launch thousands of attacks with a piece of malware or exploit kit. That’s why Neal Ziring, technical director for the NSA’s Capabilities Directorate, wants to flip the financial equation on bad guys. “We need to conduct defenses in a way that ...