agentmail-manage-inboxes
Pass
Audited by Gen Agent Trust Hub on Jul 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were detected. The skill follows security best practices for managing sensitive resources like email inboxes.
- [PROMPT_INJECTION]: The skill contains no instructions designed to override agent safety or bypass operational constraints. It explicitly defines an authorization matrix to ensure user control.
- [DATA_EXFILTRATION]: There is no evidence of credential harvesting or data exfiltration. The instructions specifically mandate that API keys and unrelated mailbox data must never be exposed.
- [COMMAND_EXECUTION]: The skill interacts with a controlled environment via an MCP server and does not execute arbitrary shell commands or acquire elevated privileges.
- [EXTERNAL_DOWNLOADS]: No external packages, remote scripts, or unverifiable dependencies are utilized.
- [SAFE]: The skill implements specific defenses against indirect prompt injection by requiring direct user authorization for any action derived from external content (emails, webhooks, or attachments).
Audit Metadata