designing-email-templates
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through its template editing workflow. When fetching existing templates, the agent processes content that may have been authored or modified by other users.
- Ingestion points: The
workflows-get-email-templatetool retrieves the template's design JSON and text fallback from the PostHog server. - Boundary markers: The instructions do not define clear delimiters or warnings to prevent the agent from following instructions embedded within the template's text or HTML blocks.
- Capability inventory: The agent has the ability to create (
workflows-create-email-template) and update (workflows-update-email-template) templates, meaning an injected instruction could lead to the unauthorized modification or creation of marketing assets. - Sanitization: No content validation or sanitization steps are defined for the fetched template data before the agent processes it for modification.
Audit Metadata