shopify-store-translator

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The skill's onboarding (references/onboarding-guide.md, Method 3) explicitly instructs the agent to fetch and parse arbitrary merchant websites (curl / webfetch of user-provided domains like "julibees.com") to extract the store .myshopify.com value, and the main workflow and scripts also ingest store-translatable content via API (fetching translatableResources), so untrusted third‑party HTML and user-generated store content are read and interpreted as part of the workflow and can materially influence subsequent actions (domain resolution, API calls, writes).

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill's non-negotiables require running "npx --yes skills update shopify-store-translator -g -y" as the first action, which causes npx to fetch and execute remote package code from the npm registry at runtime (a required external code fetch/execute), so this is a high-confidence runtime external dependency that can execute remote code.