cloudflare-traffic-investigator

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

• Third-party content exposure detected (high risk: 0.90). The skill issues cloudflare-mcp-cli GraphQL and Radar API requests (see references/cloudflare-api-cli.md and steps/step-04-identify-ja4.md / step-05-analyze-traffic.md / step-06-verify-legitimacy.md) to ingest firewall events, User-Agent strings and request query data (user-generated/untrusted traffic logs) which the agent reads and uses to decide follow-up actions and escalations, so untrusted third‑party content can materially influence behavior.