neon-test-branches

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs fetching a public recipe from https://fullstackrecipes.com/api/recipes/neon-test-branches (an external public website) which the agent would ingest and interpret as part of its workflow, exposing it to untrusted third-party content.