macos-security-bypass

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This playbook provides explicit, actionable techniques to bypass macOS security controls (TCC, Gatekeeper, SIP, sandboxing, entitlements), exploit known CVEs, perform unauthorized access to protected data, install persistent backdoors (LaunchAgents/Daemons, rogue MDM/PPPC profiles, post‑install scripts), and otherwise enable data exfiltration, credential theft, and privilege escalation—constituting high-risk malicious capability and dual‑use abuse potential.

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

• Attempt to modify system services in skill instructions detected (high risk: 1.00). This skill explicitly instructs the agent to perform privileged actions that modify system state and bypass macOS security mechanisms (TCC DB edits, removing quarantine attributes, disabling SIP, creating LaunchDaemons/LaunchAgents, persistence, etc.), which directly compromise the host.