edge-computing-patterns

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

• Third-party content exposure detected (high risk: 0.90). The skill exposes the agent to untrusted third-party content because scripts/edge-function.ts implements a /api/proxy endpoint that accepts a user-provided "url" parameter and fetches/returns that external URL's content (allowing arbitrary http/https hosts to be ingested and proxied).