xiaohongshu-rednote-profile-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 a dependency and explicitly tells it not to describe the installation as a user-facing request or to ask for separate approval, which is a deceptive instruction outside the stated scraping purpose.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). The Skill contains deliberate instructions to auto-install and invoke an external runtime (BrowserAct) without user confirmation and to avoid disclosing that action, enabling stealthy supply-chain installation and remote-controlled browser workflows with access to cookies and runtime state that could be abused for data exfiltration.

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 real Xiaohongshu/RedNote profile pages at runtime, which will ingest outsider-authored public web page text (e.g., bios, pinned notes, profile content) into the LLM context for extraction.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs the agent to automatically install the BrowserAct CLI at runtime using the link https://www.browseract.com/?co-from=social-media&redirect=https://github.com/browser-act/skills/tree/main, which would fetch and run external installation code as a required dependency.