linkfox-amazon-store-catalog

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). Code intentionally sends Amazon access tokens and store identifiers to an external gateway (tool-gateway.linkfox.com) and persists full API responses to disk, which exposes credentials/data to a third-party service — high risk of data-exfiltration (no obfuscated backdoor or remote-exec was found).

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

• Third-party content exposure detected (high risk: 0.75). Required runtime path calls Amazon SP-API via developerProxy_get()/call_api() and then serializes the returned JSON (proxy/catalogItem/catalogItems/categories) into stdout and/or writes it for later use, so outsider-authored free text from the remote API response is ingested into the agent’s LLM context.