postmark-automation
Pass
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (LOW): The skill handles untrusted data through email templates and batch message content without providing safety boundaries or sanitization guidance.
- Ingestion points: Ingestion occurs through the
POSTMARK_GET_TEMPLATEtool which retrieves HTML/Text bodies, and theTemplateModelparameter which accepts user-supplied variables. - Boundary markers: Absent. The instructions do not direct the agent to treat template content as untrusted data or to ignore embedded instructions.
- Capability inventory: High-impact capabilities include mass email delivery (
POSTMARK_SEND_BATCH_WITH_TEMPLATES) and server configuration modification (POSTMARK_EDIT_SERVER). - Sanitization: Absent. No requirement for input validation or escaping of template content is specified.
Audit Metadata