agentmail-cli

Pass

Audited by Gen Agent Trust Hub on Apr 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the agentmail-cli package globally via npm, which is a resource provided by the skill author 'agentmail-to'.
  • [COMMAND_EXECUTION]: The skill executes the agentmail command-line utility to perform operations such as creating inboxes, sending messages, and configuring webhooks.
  • [PROMPT_INJECTION]: The skill retrieves and processes external email content, which creates a surface for indirect prompt injection attacks. 1. Ingestion points: Email content is fetched via agentmail inboxes:messages retrieve in SKILL.md. 2. Boundary markers: The skill does not define specific boundaries or instructions for the agent to ignore content within messages. 3. Capability inventory: The agent has command execution capabilities via the agentmail CLI. 4. Sanitization: No content validation or sanitization steps are documented for the incoming messages.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 17, 2026, 09:07 AM