cloudinary-transformations

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly shows fetching and transforming arbitrary remote URLs (see "Fetch Remote Image" in references/examples.md and fetch delivery type examples) and also uses asset metadata/tags and conditionals (references/advanced-features.md) that the agent would read and act on, so untrusted third-party content could influence transformation choices and behavior.