resumable-ai-streams

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

• Third-party content exposure detected (high risk: 0.80). The skill instructs the agent to fetch recipe content from a public third-party URL (https://fullstackrecipes.com/api/recipes/resumable-ai-streams), meaning the agent would ingest untrusted external web content as part of its workflow and could be exposed to indirect prompt injection.