lovstudio-style-clone

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

• Third-party content exposure detected (high risk: 0.80). The workflow explicitly requires the user to paste sample articles in Step 1 of SKILL.md and then "deeply analyze" those (Step 2) and use them to drive rewrites (Step 3), so arbitrary/untrusted public or user‑generated content supplied as samples is ingested and can materially influence the agent's decisions and actions.