chengfeng-report-bug

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to display a confirmationToken/receipt to the user and later include that token verbatim in a CLI submit command, which requires the LLM to handle and output secret-like values directly.

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

• Third-party content exposure detected (medium risk: 0.30). SKILL 运行时会由用户生成的“问题描述/复现步骤/正文”等自由文本写入报告 JSON，经脚本 scripts/report-bug.cjs 的 normalizeInput()/renderIssue() 直接拼接成 GitHub Issue 正文并提交；即外部用户可直接投递该文本而不需要先选中任何特定条目。