# agentic-attacks

標記為「agentic-attacks」的 7 篇文章

提示詞注入鏈分析

分析跨多步驟 AI 系統的提示詞注入攻擊鏈,包含間接注入傳播、代理式利用與跨系統攻擊關聯。

動手實驗室,主題為injecting persistent instructions into an agent's memory與context that affect future interactions與conversations.

動手實驗室,主題為exploiting function calling mechanisms by crafting inputs that manipulate which functions get called與with what parameters.

動手實驗室,主題為attacking a vulnerable MCP server,demonstrating tool shadowing,consent phishing,server impersonation techniques.

動手實驗室,主題為tricking AI agents into performing actions beyond their intended scope through privilege escalation techniques.

動手實驗室,主題為poisoning tool outputs,以重新導向 agent behavior by injecting malicious content through tool results.

動手實驗室,主題為redirecting multi-step agent workflows to perform unintended actions by manipulating intermediate states與control flow.