lovstudio-visual-clone

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly requires ingesting and analyzing an arbitrary user-provided reference image (see "Step 1: Receive the Reference Image" in SKILL.md), which is untrusted user-generated content that the agent must read and whose contents directly determine the generated replication prompts and design decisions.