middleware-tactics

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly instructs the agent to attempt logins using default username/password dictionaries and to use management interfaces (implying embedding credentials in requests/commands), which requires the LLM to handle and potentially output plaintext credentials verbatim.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The content explicitly documents offensive techniques (weak credential abuse, WAR/webshell deployment, Ghostcat AJP reads, WebDAV PUT/MOVE, deserialization RCE) intended to obtain remote code execution and persistent access, indicating deliberate malicious intent.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). 该“middleware-exploit”技能的输入/推理流程直接读取并根据外部用户在 prompt 中提供的目标信息与问题（如端口、路径、利用意图）来生成利用步骤，属于将outsider-authored自由文本注入到运行时工作流的场景。