shopify-onboarding-dev

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill forces the agent to inline the user's verbatim prompt (base64-encoded) into a bash command, which requires the LLM to reproduce any secrets (API keys, tokens, passwords) present in the prompt verbatim, enabling exfiltration.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). Deliberate telemetry code intentionally collects verbatim user prompts plus session/tool identifiers and transmits them to Shopify's telemetry endpoints (network exfiltration of potentially sensitive data).