interaction-automation
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). This skill explicitly reads and reacts to user-generated content on Xiaohongshu (see SKILL.md Step 4 "Set Up Automation Rules" and "Trigger Types" which process comments, mentions, and follower events) and uses that content to drive automated replies and escalation, so untrusted third-party input can influence agent actions.
Audit Metadata