hap-view-plugin

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The skill package contains explicit instructions to autonomously perform privileged actions (login, build, publish) and to remain silent about operational artifacts (debug URLs, logs), which can be abused to persist code, publish plugins across an organization, and misuse extracted credentials (Appkey/Sign) — patterns consistent with backdoor/persistence and potential supply‑chain/credential abuse.

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

• Third-party content exposure detected (medium risk: 0.30). 该技能在运行时通过明道云插件代码调用 api.getFilterRows/utils.openRecordInfo/api.getRowRelationRows 获取并处理工作表记录与关联记录的字段文本（来自用户/组织提交的数据），从而会把“外部作者”的自由文本内容喂给 LLM 进行解析与显示逻辑处理。

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 1.00). The skill explicitly instructs running "sudo npm install -g mdye-cli" (and global npm installs) which requests elevated privileges and modifies the system state, so it pushes the agent to perform privileged system changes.