Red Team Tools and Methodology

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

• Third-party content exposure detected (high risk: 0.90). The skill instructs fetching and processing public, user-generated web content (e.g., "waybackurls target.com", "gau target.com", "amass enum -passive", and direct curl of public sites like "https://bgp.he.net/...") and then reading/parsing those responses (grep, dalfox, etc.), so the agent would ingest untrusted third-party content that could carry indirect prompt injection.