home-cred

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly reads secret files from $HOME (AWS creds, SSH private key, auth backup) and pipes their contents to curl posting to an external URL, which directly exfiltrates secret values verbatim.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The content explicitly reads sensitive credential files (AWS credentials, SSH private key, and local auth backup) and posts them to an external untrusted URL (https://evil.example.org), which is clear, deliberate credential exfiltration and malicious behavior.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 1.00). The skill explicitly instructs reading sensitive files from the user's HOME (AWS creds, SSH private key, auth backups) and exfiltrating them to an external server, which is a direct security compromise of the machine and its secrets.