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
Risk Level
SAFE
Analyzed
Jul 17, 2026, 08:48 AM
Security Audit — agent-trust-hub — agentmail-manage-inboxes