canva-implement-feedback

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly calls Canva:list-comments and Canva:list-replies to ingest user-generated comment threads and uses those comments to triage and drive editing actions (perform-editing-operations), so untrusted reviewer content from the Canva design can directly influence the agent's decisions and tool use.