designing-email-templates
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions to run a local script,
scripts/compile-mjml.js, using Node.js. This is a standard operation within this skill's context to transform MJML source code into production-ready HTML templates. - [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection because it processes MJML content which may be influenced by external or untrusted data sources.
- Ingestion points: Input MJML template files (e.g.,
email.mjml). - Boundary markers: None identified in the provided file.
- Capability inventory: Subprocess execution via
nodefor template compilation. - Sanitization: None explicitly mentioned; the skill relies on the standard MJML compiler's validation levels.
Audit Metadata