animation-design

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

• Third-party content exposure detected (high risk: 0.75). The skill’s runtime workflow uses WebFetch/WebSearch to retrieve outsider-authored Rive marketplace/community pages (e.g., site:rive.app/marketplace and site:rive.app/community), and then reads their page text to extract state machine/creator details—this fetched free-form content can be injected into the agent’s LLM context.

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (1 type(s) found)