securing-api-gateway-with-aws-waf

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches and displays sampled request data from AWS WAF (see SKILL.md Step 6 "Get sampled requests" and scripts/agent.py's get_sampled_requests), which are untrusted user-generated HTTP requests from the public internet that the agent reads and that are used to inform/tune WAF rules—allowing third-party content to materially influence decisions.