AIEO monitoring

AIEO 效果监控与追踪工具，用于定期监测品牌在 AI 搜索平台的可见性变化、内容质量评估和业务转化追踪。当用户提到"AIEO监控"、"AI可见性追踪"、"效果监控"、"监控报告"、"定期测试"或需要追踪品牌在AI平台表现变化时，自动调用此Skill。监控报告保存至 monitoring/ 目录，文件名格式：{品...

This is an instruction-only monitoring skill that uses browser automation to query AI platforms and save reports/screenshots locally. Before installing or running it: 1) Confirm the skill's source/trustworthiness—there is no homepage or publisher info. 2) Inspect or control the question libraries it will read (audits/positioning/* and .claude/skills/shared/question_library.md) to ensure it won't read sensitive or unrelated files. 3) Run automation in an isolated environment (dedicated VM/container) or with browsers that are not logged into personal/organizational accounts—Playwright screenshots can capture sensitive UI content and session cookies. 4) Check where monitoring/screenshots/ and monitoring/ are stored and who can access them. 5) If you expect the skill to access any credentials or post/update content (UTM guidance is present), require explicit consent and review those steps before enabling autonomous runs. If the publisher identity, intended question libraries, or explicit file-scope restrictions are provided, re-evaluate; that information would increase confidence and could move the assessment toward benign.

Type: OpenClaw Skill Name: moments-aieo-monitoring Version: 1.0.0 The skill bundle provides a framework for 'AI Engine Optimization' (AIEO) monitoring, which utilizes high-risk capabilities including general shell access (Bash) and a full suite of Playwright browser automation tools. The instructions in SKILL.md and tools_guide.md direct the agent to automate interactions with multiple third-party AI platforms (such as doubao.com, kimi.moonshot.cn, and chat.openai.com), including the handling of authenticated sessions. While these actions are consistent with the stated purpose of tracking brand visibility, the combination of broad automation tools and the requirement to interact with external authenticated services represents a significant attack surface and potential for abuse, meeting the criteria for risky capabilities without explicit malicious intent.