multi-protocol-bridge

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill requires embedding credentials and private keys verbatim in URLs and request fields (e.g., username:password in scheme://username:password@host and options.private_key), which forces the LLM to handle and output secret values directly.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). This skill is not obviously a stealthy backdoor, but it exposes powerful primitives (arbitrary SSH command execution, file upload/download, and arbitrary MQTT publishing) and accepts credentials/keys in requests — features that directly enable data exfiltration, remote code execution, credential misuse, and system compromise and therefore present a high abuse risk if used by untrusted agents or attackers.