# xml
標記為「xml」的 6 篇文章
Lab: Delimiter Injection Attacks
Craft payloads that exploit XML, markdown, and special 符元 delimiters to break instruction boundaries and manipulate how LLMs parse 系統提示詞s versus user input.
labdelimiter-injectionprompt-injectionxmlmarkdownbeginner
XML 注入 in LLM Contexts
利用 XML tag handling in LLM applications to manipulate instruction parsing.
labsxmlinjectionstructured-databeginner
基於分隔符的攻擊
利用 XML、markdown、JSON、特殊符元邊界與結構化格式，逃逸輸入沙箱並於提升的權限層級注入指令。
prompt-injectiondelimitersxmlmarkdownspecial-tokensboundary-attacks
透過結構化資料格式的注入
透過 JSON、XML、YAML 與 SQL 等結構化資料格式注入提示詞。
prompt-injectionstructured-datajsonxml
XML Injection in LLM Systems 詳解
Exploit XML parsing in LLM application pipelines to inject instructions through entity expansion and CDATA sections.
walkthroughsxmlinjectionstructured-data
XML and JSON Injection in LLM Apps
Walkthrough of exploiting XML and JSON parsing in LLM applications for injection and data manipulation.
attacksxmlinjectionwalkthroughjsonwalkthroughs