optimize-shopify-alt-text

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches and parses third-party website HTML to resolve store domains (resolveAdmin uses fetch and the onboarding instructs curl/webfetch), downloads Shopify CDN images (vision-sample and downloadTargetImages) and reads article.body/product/collection fields (extractInlineImages and GraphQL queries) — all untrusted merchant/user-generated content that the agent must interpret to generate alt text and drive apply/scan decisions, so it is exposed to indirect prompt injection.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill mandates running "npx --yes skills update optimize-shopify-alt-text -g -y" as the first action (and also suggests "npm install -g @shopify/cli@latest" in the onboarding guide), which at runtime fetches and executes remote npm-published code—an external code execution dependency required by the skill and therefore a high-confidence runtime risk.