xiaohongshu-search-full

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to read page security tokens (xsec_token) and signed video URLs from search results/detail pages and include them verbatim in navigation commands and outputs, which requires the LLM to handle and emit secret values directly.

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

• Third-party content exposure detected (medium risk: 0.30). Source: the Xiaohongshu search workflow reads outsider-authored note text (title and body/desc) from user-driven pages on https://www.xiaohongshu.com/search_result/ and subsequent https://www.xiaohongshu.com/explore/{id}?xsec_token=... note detail pages, then performs matching and returns those text fields to the user.