modernize-flp-sandbox

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

• Third-party content exposure detected (medium risk: 0.30). SKILL.md at runtime ingests outsider-authored free text from the user’s local UI5 project files—specifically it reads legacy HTML and JS under $APP_ROOT/webapp/test/ and $APP_ROOT/webapp/ (including parsing externalized and inline config content, plus extracting inline script blocks and scanning code via regex/greps), so the attacker can provide poison by modifying those files before invoking the skill.