shopware-admin-crud-module

Pass

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from user arguments (entity names, fields, prefixes) and local files (Shopware EntityDefinitions) to populate code templates. While this is the intended functionality, it establishes a potential ingestion surface for untrusted content.
  • Ingestion points: User-provided entity configuration and local PHP definition files.
  • Boundary markers: The instructions do not define specific delimiters or "ignore" instructions for the ingested data.
  • Capability inventory: The skill involves reading local project files and writing new administration components.
  • Sanitization: The instructions do not explicitly mandate input validation or sanitization.
  • [SAFE]: The skill consists entirely of markdown documentation and reference templates for Shopware development. It does not contain any hidden scripts, network operations, or persistence mechanisms. All code patterns follow standard Shopware Administration guidelines.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 23, 2026, 07:27 AM