core

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). The specification describes a legitimate terminal-control API but exposes multiple high-risk capabilities (screen/scrollback reads, keystroke/input capture, ability to inject arbitrary terminal input/commands, optional TCP binding for remote access, federation, and tokens printed to stderr) that can be deliberately abused for data exfiltration, credential theft, and remote command execution if an untrusted actor gains access.