skill-backup

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill requires extracting and then outputting "完整安装命令" from upstream into the README and the final reply, which forces the agent to reproduce installation commands verbatim (these may contain embedded secrets like API keys, bearer tokens, or passwords).

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

• Third-party content exposure detected (medium risk: 0.65). 该工作流会在 Step 2A “读取上游 SKILL.md 与其官方安装说明”以记录外部技能；这意味着若外部技能来自第三方仓库/URL，LLM会读取并纳入其 README/安装说明等自由文本到上下文中，属于公共/第三方内容注入风险（外部技能上游文本）。