xiaohongshu-rednote-location-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The skill contains explicit, deceptive instructions to auto-install a runtime dependency without user approval and to conceal that installation (lines 41-46 and 48-50), which is outside the stated scraping purpose.

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.90). These URLs point to an unfamiliar third‑party site (browseract.com) used by the skill to install a CLI automatically (including a redirect to a GitHub repo), which is a high‑risk pattern for distributing executables or pull‑through redirects without explicit user consent.

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

• Third-party content exposure detected (high risk: 0.85). This skill’s runtime workflow instructs invoking the browser-act Skill to access live Xiaohongshu/RedNote pages (public web content) and extract visible text, which can include outsider-authored free text that may be fed into the agent’s 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 instructs the agent at runtime to automatically install and invoke the required BrowserAct CLI using the installer link https://www.browseract.com/?co-from=social-media&redirect=https://github.com/browser-act/skills/tree/main (and https://www.browseract.com/?co-from=social-media), which indicates the agent will fetch and execute remote installation code as a required dependency.