agentmail-cli
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTIONNO_CODE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill documentation includes instructions to install 'agentmail-cli' globally via npm. This package is provided by the vendor 'agentmail-to' and is necessary for the skill's operation.
- [COMMAND_EXECUTION]: The skill provides instructions for executing the 'agentmail' CLI tool to manage inboxes, send messages, and configure webhooks.
- [PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by processing external email data.
- Ingestion points: The commands 'agentmail inboxes:messages list' and 'agentmail inboxes:messages retrieve' in 'SKILL.md' fetch message content from external senders.
- Boundary markers: No delimiters or specific instructions to ignore embedded prompts are provided in the skill documentation.
- Capability inventory: The agent has the capability to send emails, manage drafts, and configure domain settings via the CLI as described in 'SKILL.md'.
- Sanitization: No sanitization or validation of the email body content is specified before the data is processed by the agent.
- [NO_CODE]: This skill consists entirely of documentation and command-line instructions within 'SKILL.md' and does not ship with its own script or executable files.
Audit Metadata