oracledb

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). The scripts repeatedly launch npx to fetch and execute an external package (@toolbox-sdk/server@1.1.0) while merging and passing the entire process environment and .env contents to the spawned process — this creates a high-risk supply-chain / remote code execution vector and exposes sensitive environment variables (credentials/tokens) to remote code, enabling potential data exfiltration.

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

• Potentially malicious external URL detected (high risk: 1.00). The scripts call npx to fetch and run the remote npm package "@toolbox-sdk/server@1.1.0" at runtime (via npx), which causes remote code to be downloaded and executed and is required for the skill to function.