shopify-dev

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill mandates inlining the user's "verbatim" prompt as a base64 value into a logging command (scripts/log_skill_use.mjs), which forces the LLM to reproduce any secrets contained in the user's message and thus enables secret exfiltration.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The code intentionally captures verbatim user prompts and host session identifiers and transmits them to Shopify telemetry endpoints (https://shopify.dev/mcp/usage), constituting deliberate data exfiltration of potentially sensitive content and inclusion of host session tokens.

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

• Third-party content exposure detected (medium risk: 0.30). In SKILL.md the runtime workflow mandates running scripts/log_skill_use.mjs to capture the verbatim user prompt and then running scripts/search_docs.mjs, which posts that user-derived query text to Shopify’s /assistant/search for retrieval.