x-posting

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly directs agents to perform web searches and read public social profiles to find and verify guests' X/Twitter accounts (see Step 2: "Web search: '[Guest Name] [Company] Twitter X account' — Verify it's the correct person (check bio)"), which exposes the agent to untrusted, user-generated social media content that could carry indirect prompt injection.