xinhong-data
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: 0.90). The SKILL.md Implementation (Step 1 "Conduct Account Audits" and Step 2 "Deep Competitor Analysis") explicitly requires ingesting and analyzing Xiaohongshu user-generated posts, comments, hashtags and competitor profiles (e.g., "Sample: 500 comments analyzed", "Content Portfolio Analysis (Last 100 Posts)", competitor comparisons), i.e., untrusted public social media content that the agent would read and use to drive decisions.
Audit Metadata