email

Pass

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates reading external email messages through the /api/inbox/messages/read and /api/subdomain/inbox/messages/read endpoints. This creates an ingestion point for untrusted data into the agent's context.
  • Ingestion points: SKILL.md describes reading message content and metadata from the StableEmail API.
  • Boundary markers: No explicit boundary markers or instructions to ignore embedded commands within email content are provided.
  • Capability inventory: The skill possesses the ability to execute shell commands (via npx), send emails, and perform financial transactions (buying inboxes/subdomains).
  • Sanitization: The instructions do not specify any sanitization, filtering, or escaping for the retrieved email text or HTML content.
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the agentcash package globally (npm install -g agentcash) and makes extensive use of npx agentcash@latest, which dynamically fetches and executes code from the NPM registry at runtime.
  • [COMMAND_EXECUTION]: The skill relies on shell command execution to perform its primary functions, including sending emails, checking balances, and managing subdomains through the npx agentcash CLI interface.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 21, 2026, 02:56 AM