From 73a93403260dcd7494a8b3f79ef8192e1e384406 Mon Sep 17 00:00:00 2001 From: Bill Sempf Date: Thu, 5 Mar 2026 18:54:35 -0500 Subject: [PATCH] Added concole config atttacks issue 2044 --- cheatsheets/AI_Agent_Security_Cheat_Sheet.md | 1 + 1 file changed, 1 insertion(+) diff --git a/cheatsheets/AI_Agent_Security_Cheat_Sheet.md b/cheatsheets/AI_Agent_Security_Cheat_Sheet.md index c47b52e202..72a78dcebf 100644 --- a/cheatsheets/AI_Agent_Security_Cheat_Sheet.md +++ b/cheatsheets/AI_Agent_Security_Cheat_Sheet.md @@ -13,6 +13,7 @@ AI agents are autonomous systems powered by Large Language Models (LLMs) that ca - **Goal Hijacking**: Manipulating agent objectives to serve attacker purposes while appearing legitimate. - **Excessive Autonomy**: Agents taking high-impact actions without appropriate human oversight. - **Cascading Failures**: Compromised agents in multi-agent systems propagating attacks to other agents. +- **AI Console Malicious Configuration**: AI developer consoles can be compelled to consume data that contains instructions driving malicious changes to the underlying LLM configuration. - **Denial of Wallet (DoW)**: Attacks causing excessive API/compute costs through unbounded agent loops. - **Sensitive Data Exposure**: PII, credentials, or confidential data inadvertently included in agent context or logs.