cargo-mailbox-management

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes external content from email replies and message threads.
  • Ingestion points: Data enters the agent's context through message snippets and thread details retrieved from the Cargo backend via commands like cargo-ai mailboxManagement thread get and cargo-ai mailboxManagement event list.
  • Boundary markers: There are no explicit instructions to use delimiters or sanitization when the agent processes retrieved email content.
  • Capability inventory: The skill has the ability to execute CLI commands that perform write operations, such as provisioning mailboxes and sending emails.
  • Sanitization: No explicit sanitization or filtering of external content is mentioned.
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the @cargo-ai/cli package from npm to function.
  • [COMMAND_EXECUTION]: The skill relies extensively on executing the cargo-ai CLI tool to perform mailbox management tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 05:51 AM
Security Audit — agent-trust-hub — cargo-mailbox-management