shopify-developer

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly instructs the agent to fetch real-time documentation from a third-party public API (e.g., the "API Drift Test" curl commands to https://context7.com/api/v2/ and the recommendation to install the Context7 skill) so the agent will read and interpret external, non‑trusted web content as part of its workflow, which could enable 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 explicitly performs runtime fetches from Context7 (e.g. https://context7.com/api/v2/libs/search?libraryName=shopify+liquid?query=metafields and https://context7.com/api/v2/context?libraryId=/shopify/liquid&query=metafield+access&type=txt) to "verify current patterns" and relies on that fetched documentation to determine coding/instruction decisions, so external content can directly influence agent prompts/behavior.