inttegro-message-templates
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill connects to the official vendor domain
mcp.inttegro.comto provide template management and messaging capabilities via the Model Context Protocol (MCP).\n- [SAFE]: Instructions explicitly discourage the use of secrets or credentials in variable defaults, adhering to secure configuration practices.\n- [SAFE]: A multi-stage review process (draft, preview, publish) is enforced, requiring the agent to verify rendered content for safety and correctness before any customer-facing actions are performed.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes template data which could potentially contain malicious instructions from external sources.\n - Ingestion points: Message template bodies and variable definitions loaded via
get_message_templateandpreview_message_template(SKILL.md).\n - Boundary markers: The instructions require a manual review of the rendered SMS/email content for "unsafe output" before publishing.\n
- Capability inventory: The skill has the ability to send rendered templates to customers using
send_customer_template.\n - Sanitization: Safety is maintained through required confirmation of the final rendered copy before sending.
Audit Metadata