xhs-search

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly requires displaying feed results including xsec_token (a session/token value) which forces the LLM to output sensitive token values verbatim, creating an exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly calls search_feeds on Xiaohongshu (小红书) in steps 2–3 and displays user-generated notes (titles, authors, feed_id/xsec_token), meaning the agent ingests and interprets public social-media content that could influence subsequent actions.