Attack on AI agents’ external resources risk for AI
Description
Attackers intentionally create vulnerabilities or exploit existing vulnerabilities in external resources (tools/database/applications/services/other agents) that AI agents rely on to execute their intended actions or to achieve their goals.
Why is attack on ai agents’ external resources a concern for foundation models?
Compromised external resources could impact the AI agent’s performance in different ways, such as manipulating AI agents to pursue a different goal, manipulating AI agents to execute undesired actions, capturing and relaying interactions between AI agents to malicious actors, and getting AI agents to share personal or confidential information.
Parent topic: AI risk atlas
We provide examples covered by the press to help explain many of the foundation models' risks. Many of these events covered by the press are either still evolving or have been resolved, and referencing them can help the reader understand the potential risks and work toward mitigations. Highlighting these examples are for illustrative purposes only.