umbraco-add-data-type

Pass

Audited by Gen Agent Trust Hub on Oct 26, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes site schema data which acts as a potential injection surface. 1. Ingestion points: CMS data types and document types read via MCP tools like get-all-data-types (workflow.md). 2. Boundary markers: No delimiters are used for site data, but the skill follows a rigid requirements documentation structure. 3. Capability inventory: The skill can create and update data types and document types using MCP tools (workflow.md). 4. Sanitization: All proposed schema modifications are subject to a mandatory user approval gate ('Step 5: Approve') before execution.
  • [COMMAND_EXECUTION]: The skill utilizes legitimate Umbraco CMS management tools and a validation utility (umbraco-skill-evaluator). These tools are used for their intended administrative purpose and are protected by manual approval checkpoints.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 26, 2026, 04:11 PM