muapi-rednote-cover

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

• Third-party content exposure detected (high risk: 0.70). The skill's SKILL.md explicitly accepts an optional reference_image (type image_url) and instructs the agent to use muapi image edit with that image, meaning the agent will fetch and incorporate arbitrary user-supplied/public images from the web into its generation workflow (untrusted third‑party content that can influence behavior).