hyva-create-module

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill facilitates shell command execution, specifically bin/magento setup:upgrade, by leveraging the hyva-exec-shell-cmd requirement to handle environment-appropriate wrappers.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied parameters and interpolates them into file templates, creating a surface for indirect prompt injection.\n
  • Ingestion points: The parameters vendor, module, description, dependencies, and composer_require defined in SKILL.md are entry points for external data.\n
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are used for these parameters.\n
  • Capability inventory: The skill can write to the local file system (app/code/) and trigger shell command execution via its dependencies.\n
  • Sanitization: Input validation is limited to PascalCase checks for the vendor and module parameters, while other fields lack validation, allowing potentially unsafe content to be included in configuration files like composer.json.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 06:41 AM
Security Audit — agent-trust-hub — hyva-create-module