aws-expert

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill prompt includes hard-coded secret values (e.g., "MySecurePassword123") embedded in commands/JSON, which would require the LLM to reproduce secrets verbatim in outputs — a direct secret-exfiltration risk.

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

• Attempt to modify system services in skill instructions detected (high risk: 0.70). The skill includes a user-data script that runs privileged system commands (yum update/install, systemctl start/enable, docker run) which modify the host system and require root privileges, so it pushes actions that can change the machine's state.