security-reviewer

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

• Third-party content exposure detected (high risk: 0.80). The skill's penetration-testing reference (references/penetration-testing.md) and core workflow direct the agent to fetch and interpret public internet data (e.g., curl to crt.sh, amass/subfinder outputs, nmap/whatweb scans, unauthenticated S3 queries) as part of reconnaissance, so untrusted third-party content is read and can materially influence subsequent testing actions.