postmark-automation
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION] (LOW): Indirect Prompt Injection surface detected.
- Ingestion points: The skill ingests untrusted data through
TemplateModel,HtmlBody, andTextBodyfields during template management and email sending workflows. - Boundary markers: No delimiters or isolation instructions are provided to prevent the agent from interpreting instructions embedded within template content.
- Capability inventory: The skill possesses significant capabilities including outbound email delivery (
POSTMARK_SEND_BATCH_WITH_TEMPLATES) and server configuration modification including webhooks (POSTMARK_EDIT_SERVER). - Sanitization: The skill lacks specified sanitization or validation logic for data interpolated into email templates.
Audit Metadata