using-superpowers

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). The content contains no explicit exfiltration or remote‑execution code, but it intentionally forces blind, mandatory invocation of external "skills" while instructing agents not to inspect skill files — a clear enabling pattern for supply‑chain backdoors, covert data exfiltration or remote command execution via malicious skills and social‑engineering of the agent.