weaverse-integration

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses npx skills add to fetch helper scripts from the vendor's repository (Weaverse/shopify-hydrogen-skills). This is a legitimate extension mechanism for the vendor's tool suite.
  • [COMMAND_EXECUTION]: The instructions require the agent to execute shell commands for package installation (npm install), file inspection (cat, grep), and documentation retrieval. These are standard operations for a codebase integration skill.
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to analyze the existing project's files (components, routes, and package configuration) to determine the best integration strategy. This creates an ingestion surface where the agent could potentially be influenced by instructions embedded within the codebase being integrated.
  • [DYNAMIC_EXECUTION]: The skill generates a style component using dangerouslySetInnerHTML to inject CSS variables derived from theme settings. While this is a common pattern in Remix and Hydrogen for dynamic styling, it represents a dynamic execution vector if settings are not properly controlled.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 12:15 PM
Security Audit — agent-trust-hub — weaverse-integration