playwright-tests

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly instructs fetching a recipe from the public site fullstackrecipes.com (curl https://fullstackrecipes.com/api/recipes/playwright-tests), so the agent would ingest content from an external, publicly hosted source which could be untrusted and enable indirect prompt injection.