help-center-design

Warn

Audited by Snyk on Feb 23, 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's "Trend Awareness Protocol" explicitly requires the agent to run quick web searches and prefer sources flagged in data/sources.json (see "REQUIRED: When users ask... run a quick web search" and the "Required Searches" list), meaning the agent will fetch and interpret public third-party content to drive recommendations and actions, enabling indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 23, 2026, 08:16 PM