agent-email-cli
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install the
@zaddy6/agentemailpackage globally via npm or bun. This package is a vendor-owned resource provided by the skill author. - [COMMAND_EXECUTION]: The skill operates by executing
agent-emailcommands in the system shell to manage email profiles and messages. - [PROMPT_INJECTION]: The skill creates an indirect prompt injection surface because it retrieves and reads content from external emails.
- Ingestion points: Content is retrieved via
agent-email readandagent-email showinSKILL.md. - Boundary markers: There are no instructions to use delimiters or ignore embedded commands within the email bodies.
- Capability inventory: The agent can execute shell commands to create, list, and delete accounts and messages.
- Sanitization: The skill does not define any sanitization or validation for email content before it is processed by the agent.
Audit Metadata