email-resend

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill ingests untrusted user input from form data and interpolates it directly into HTML email templates within the sendContactEmail and sendBookingEmail functions. Ingestion points: Ingestion occurs via the formData object in the submitContactForm server action. Boundary markers: Input is validated using the contactFormSchema.safeParse method, though explicit delimiters or 'ignore' instructions are absent. Capability inventory: The skill has the capability to send outbound communications through the resend.emails.send API. Sanitization: User-controlled strings (name, message, phone, injuries) are placed into HTML templates without proper escaping, allowing for potential HTML injection in the recipient's email client.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:33 PM