agentic-system-design

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly spawns verification/analysis sub-agents that call web_search and apify_top_posts (see references/case-marketing.md and the sub-agent spawn rules in the examples and case studies), so the agent is expected to ingest public web/social content and act on it, allowing untrusted third-party content to materially influence tool use and decisions.