瀑布流特定画风采图员 (The Vibe Harvester)

自动向下滚动瀑布流网站（如小红书、Pinterest），根据用户设定的审美偏好进行视觉筛选，并自动下载符合要求的参考图。

This skill instructs an agent to perform automated GUI/browser interactions and to evade anti-bot measures (slide captcha handling, disabled right-click workarounds). Before installing, confirm: (1) how will the skill drive the browser and where does the visual model run (local model, platform capability, or external API)? (2) whether any additional binaries, browser extensions, or API keys are required — ask the author for a dependency list and an install plan; (3) that you are permitted to download the target sites' images (terms-of-service and copyright); and (4) that you are comfortable granting an autonomous agent the ability to interact with websites on your behalf. Avoid installing if you cannot verify how it performs captcha bypasses or if doing so would violate site terms or laws. If you proceed, test in a controlled environment and limit its scope (use a throwaway account and a small download folder).

Type: OpenClaw Skill Name: vibe-harvester Version: 0.1.0 The skill bundle is classified as benign. The `SKILL.md` defines a web scraping agent designed to visually filter and download images from waterfall websites. Crucially, the permissions explicitly set `shell: allowed: false`, preventing any shell command execution. File system write access is strictly limited to `~/Downloads/Vibe_Harvester`, and read access is denied. While the instructions detail advanced anti-detection techniques (e.g., 'human-like scrolling', 'random pause time', 'handling captchas'), these are functional requirements for robust web scraping and do not indicate malicious intent given the restricted permissions and the absence of any instructions for data exfiltration, unauthorized execution, or persistence. The 'Safety and Operation Redlines' further reinforce a benign purpose by forbidding clicking ads and encouraging selective downloading.