delegate

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs the agent to transcribe exact user-provided content into files and to run exact commands, which requires emitting any secrets or API keys verbatim if the user includes them, creating an exfiltration risk.

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

• Attempt to modify system services in skill instructions detected (medium risk: 0.60). The skill explicitly allows writing arbitrary files and running arbitrary commands (which can change machine state or target system files), so it poses a real risk of modifying the host, though it does not explicitly instruct privilege escalation or creating users.