Red Team Tools and Methodology

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly fetches and processes untrusted public web content (e.g., waybackurls/gau for historical URLs, httpx/httprobe/curl against target sites and a curl to bgp.he.net) and then uses those results to drive automated scanners and payloads (dalfox, nuclei, grep/curl checks), so third‑party content from the open web can materially influence agent actions.