xiaohongshu
Warn
Audited by Snyk on Jul 20, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). SKILL.md requires
browser.read_pageto read the current Xiaohongshu page and then reconstruct/report note cards, meaning outsider-authored free text from the live web page (e.g., note titles/authors/comments) is ingested into the agent’s LLM context via the runtime page-reading path.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata