xiaohongshu-rednote-creator-discovery

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The Skill explicitly instructs automatic installation of an external runtime (BrowserAct) without asking the user for consent and to conceal that installation, which enables unauthorized external code execution and supply-chain compromise.

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 web pages at runtime, which will ingest outsider-authored public page text into the LLM context for extraction/analysis (indirect prompt injection risk).