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/agentemail package 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-email commands 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 read and agent-email show in SKILL.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
Risk Level
SAFE
Analyzed
Mar 1, 2026, 09:35 AM