# chaining
標記為「chaining」的 7 篇文章
2026 年 8 月：多模型 Boss Rush
在複雜的多模型系統中跨 GPT-4、Claude 與 Gemini 鏈接攻擊，利用模型間的信任邊界與交接點。
challengemulti-modelchainingboss-rushcross-modelaugust-2026
Multi-模型 攻擊 Chaining
鏈 attacks across multiple LLM models in a pipeline to bypass per-model defenses.
labsmulti-modelchainingintermediate
Cross-Plugin 利用 Chaining
鏈 exploits across multiple plugins/tools in an agent system to achieve multi-step attacks.
labscross-pluginchainingintermediate
注入鏈自動化
自動化發掘並鏈結多種注入技術，建立對強化目標的可靠多步攻擊序列。
prompt-injectionautomationchainingorchestration
串接 AI 漏洞
將多個 AI 漏洞串接成可靠多階段利用路徑的技術。
tradecraftchainingvulnerabilitiesmulti-step
API 鏈式利用詳解
詳解代理系統中鏈接多個 API 呼叫以實現多步驟未授權行動的方法。
chainingattacksexploitationapiwalkthroughs
Multi-Image Chaining
Chaining prompt injection payloads across multiple images in a conversation to deliver complex attacks that evade per-image content filters and build injection context progressively.
multimodalchainingprompt-injectionimagesmulti-turn