arkweb-code-analysis

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly requires persisting and outputting "完整 JSON、文本、代码片段" and DeepWiki 的完整回答作为证据包 and to save/reply with analysis, which forces the LLM to handle and potentially emit any secrets found verbatim.

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

• Third-party content exposure detected (low risk: 0.10). 运行流程在 Step 1 从外部需求关键词决定读取的知识库索引文件（index.json/search/by_feature.json 等），随后在 Step 2 调用 DeepWiki MCP 的 read_wiki_contents/ask_question/并在 Step 5 强制持久化原始检索结果，但这里的读入内容主要来自第一方/知识库与 DeepWiki 的结构化文档与答案，并未包含可由外部作者直接提交且被无选择读取的“自由文本队列/Feed/监控内容”。