cargo-mailbox-management

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill documents the installation and use of the @cargo-ai/cli Node.js package. This is the official command-line tool for the Cargo platform and is used to execute all mailbox management functions.
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of inbound email replies, which could potentially contain malicious instructions intended to influence the AI agent.
  • Ingestion points: The thread get and event list commands, as described in SKILL.md and references/response-shapes.md, are used to retrieve the body and snippets of external email replies.
  • Boundary markers: The documentation does not define specific delimiters or instructions for the agent to distinguish between its own operational instructions and the untrusted content of the email replies.
  • Capability inventory: The skill possesses the capability to send further emails and manage infrastructure components like mailbox suppression lists and provisioning.
  • Sanitization: No explicit mention is made regarding the sanitization or filtering of reply content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 08:20 AM