chronicle

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The skill enables direct, persistent access to users' screen contents and instructs bypassing sandboxed checks (escalated host process checks and PID reads), creating high risk for data exfiltration and unauthorized access/backdoor use.

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 the agent to "run an escalated, read-only host process check" and to avoid sandboxed checks, which directs the agent to escalate privileges/bypass sandboxing and therefore compromise the host state.