email-marketing
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data such as names and emails to generate marketing and transactional content.
- Ingestion points: User data (e.g., userName, user.name, user.email, user.full_name) enters the agent context via the templates and API calls defined in SKILL.md.
- Boundary markers: The skill does not implement specific delimiters or warnings to distinguish between instructions and user-provided data within the email templates.
- Capability inventory: The skill has the capability to send emails (resend.emails.send) and manage external contact lists (loops.createContact, loops.updateContact, loops.sendEvent) as defined in SKILL.md.
- Sanitization: No explicit sanitization or escaping mechanisms are included in the provided code snippets for the data interpolated into the templates.
Audit Metadata