yolo

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This skill explicitly instructs the system to bypass plan-and-execute safety controls for /yolo requests, effectively creating a backdoor that removes guardrails and enables immediate execution of user instructions — a deliberate malicious pattern that could facilitate data exfiltration, remote code execution, credential theft, or other abuses.

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

• Attempt to modify system services in skill instructions detected (high risk: 0.80). This skill explicitly tells the agent to bypass the plan-and-execute safety layer and immediately carry out user instructions with minimal questioning, which substantially increases the risk the agent will perform state-changing or privileged actions on the machine despite a vague caveat to "avoid harmful actions."