canva-branded-presentation

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

• Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md workflow Step 1 explicitly reads user-provided Canva designs (via design links, Canva:search-designs and Canva:start-editing-transaction), which are third-party/user-generated content the agent ingests and that can influence subsequent generation and tool actions.