game-assets

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

• Third-party content exposure detected (high risk: 0.90). Flagged because SKILL.md and integration-patterns.md (and character-pipeline.md) explicitly instruct using WebSearch and downloading arbitrary public web content—company logos, photos, and meme images (including thread.json image_url) via curl/wget—into public/assets and then loading/studying those untrusted, user-generated sources as part of the character/asset-building workflow, which the agent is expected to read and act on.