red-team-tools

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly ingests and processes public, untrusted third-party content—e.g., commands like "waybackurls target.com | tee wayback.txt", "gau target.com", "curl -s 'https://bgp.he.net/...'", and amass/subfinder outputs—and then uses those results to drive scanning/fuzzing tools (ffuf, dalfox, nuclei), so external web content can materially influence agent actions.