xiaohongshu-user-profile

Warn

Audited by Snyk on Jun 13, 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). The skill navigates to a Xiaohongshu user profile page and then executes JS to read window.__INITIAL_STATE__ (including user.userPageData and user.notes) from the remote site; this page content is authored/published by an outsider (the Xiaohongshu user) and is ingested as readable JSON text into the agent’s LLM context via the eval "$(python scripts/extract-*.py ...)" outputs.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 13, 2026, 04:39 AM
Issues
1
Security Audit — snyk — xiaohongshu-user-profile