user-persona-analysis

Warn

Audited by Snyk on Mar 5, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 1.00). The skill's required workflow includes exporting and analyzing user-generated comments from Xiaohongshu posts ("Step 1: Comment Analysis" in SKILL.md) and references using third‑party analytics (Qiangua Data), so the agent ingests untrusted public content that directly informs decisions and next actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 5, 2026, 11:40 AM