extension-email-verification

Pass

Audited by Gen Agent Trust Hub on Oct 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of several dependencies within the Caffeine AI ecosystem.
  • The Motoko packages caffeineai-email-verification and caffeineai-email are retrieved via the mops package manager.
  • The frontend React hook is provided by the @caffeineai/email-verification NPM package.
  • These resources are vendor-provided extensions intended for the implementation of the core verification functionality.
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to process and send emails containing dynamic content, which introduces a potential surface for indirect prompt injection if not handled carefully.
  • Ingestion points: The htmlBody, subject, and recipients parameters in the registerUser function in SKILL.md ingest data that may be sourced from untrusted inputs.
  • Boundary markers: The skill uses the {{VERIFICATION_URL}} placeholder for link injection, but the instructions do not specify the use of delimiters or 'ignore' instructions for the rest of the email body.
  • Capability inventory: The skill possesses the capability to perform network-based email transmission via the platform's INTEGRATIONS_GATEWAY_URL using sendVerificationEmail in SKILL.md.
  • Sanitization: The implementation instructions and examples do not explicitly demonstrate content sanitization or HTML escaping for the variable data interpolated into the email template.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 29, 2026, 08:57 PM