extension-email-marketing

Pass

Audited by Gen Agent Trust Hub on Oct 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The setup process involves standard administrative tasks requiring the execution of package manager commands (mops add and npm install) to fetch vendor-specific libraries.
  • [INDIRECT_PROMPT_INJECTION]: The skill uses a template system to personalize emails, which creates a potential surface for indirect injection if user-controlled data is not properly handled.
  • Ingestion points: Untrusted data enters the context via the name field in UserProfile (set during registration) and the htmlBody provided by admins.
  • Boundary markers: The skill uses double-curly-brace placeholders (e.g., {{NAME}}, {{UNSUBSCRIBE_URL}}) to mark where dynamic content is inserted.
  • Capability inventory: The skill possesses the capability to send emails to external recipients via a mail gateway using platform-provided credentials (INTEGRATIONS_GATEWAY_API_KEY).
  • Sanitization: The example code does not demonstrate explicit sanitization or HTML escaping of the user-provided name before it is interpolated into the email body.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 29, 2026, 08:57 PM