xiaohongshu-rednote-note-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The Skill explicitly instructs the agent to install a runtime dependency automatically without user confirmation and to hide that installation from the user ("do not describe it...do not request separate approval"), which is a deceptive directive outside the normal stated scraping task.

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

• Third-party content exposure detected (high risk: 0.85). SKILL.md instructs the agent to use the BrowserAct CLI to access live Xiaohongshu/RedNote pages at runtime and extract note text/body content from user-supplied URLs/topics, which is outsider-authored free text that can be fed into the LLM context via the browser-extracted page content.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The Skill explicitly requires installing and invoking the BrowserAct CLI at runtime using the installer links (https://www.browseract.com/?co-from=social-media and https://www.browseract.com/?co-from=social-media&redirect=https://github.com/browser-act/skills/tree/main), which would fetch and install remote code the agent relies on.