superhuman

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches and reads arbitrary user emails and provider-synced content from Superhuman/Gmail/Microsoft Graph (e.g., "superhuman read " and "superhuman ai 'summarize this thread'"), so the agent ingests untrusted, user-generated third‑party content that can materially influence decisions and automated actions like drafting or sending replies.