lovstudio-style-clone

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

• Third-party content exposure detected (high risk: 0.90). The skill's mandatory workflow (SKILL.md Step 1 and Step 2) requires the agent to ingest and deeply analyze sample articles that the user must paste (user-provided / potentially public third-party content), and those samples directly determine rewriting behavior, so untrusted external text could inject instructions that change the agent's actions.