web-app-security-audit

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

• Third-party content exposure detected (high risk: 0.80). The skill's workflow explicitly requires fetching and interpreting content from the target application's public endpoints (e.g., checking robots.txt, sitemap.xml, curling target URLs and headers with "curl -s -I ", enumerating exposed pages and admin paths, and inspecting returned HTML/JS), which are open/public third-party sources whose content the agent must read and which can materially influence subsequent tests and findings.