ai-llm-inference

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md Trend Awareness Protocol explicitly requires the agent to "MUST use WebSearch" (with four required searches) and to report findings, so the agent will fetch and interpret public web content (and references listed in data/sources.json) that can influence recommendations.