maxhub-douyin

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The package/documentation contains explicit instructions to collect and transmit sensitive session cookies to a third‑party API and includes an endpoint that explicitly facilitates fraudulent view‑count inflation, indicating deliberate facilitation of credential exfiltration and abuse.

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

• Third-party content exposure detected (high risk: 0.72). Runtime path: the skill calls MaxHub endpoints (e.g., Search/Trending/Video APIs) and then feeds the returned JSON fields like video descriptions, author nicknames/signatures, and comment/word lists (outsider-authored user-generated text) into the agent’s LLM context for summarization/analysis.