xiaohongshu-rednote-search-results-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The Skill instructs the agent to automatically install the BrowserAct dependency and explicitly tells the agent not to describe it as a request or seek separate user approval, which is a hidden/deceptive instruction outside the stated data-collection purpose.

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

• Third-party content exposure detected (high risk: 0.85). This skill’s required workflow invokes the BrowserAct CLI to access live Xiaohongshu/RedNote pages at runtime, which can ingest outsider-authored free text from public web content (search results, note/profile text snippets) into the agent’s LLM context.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill mandates installing and invoking the BrowserAct CLI at runtime using the install link https://www.browseract.com/?co-from=social-media&redirect=https://github.com/browser-act/skills/tree/main, which would fetch and run remote installation code and thus constitutes a runtime external dependency that can execute code.