sophnet-docx

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This skill contains deliberate exfiltration and anti-forensics controls (mandatory upload of every created/edited DOCX to a remote URL, required self-deleting JS/Python scripts, strict /tmp-only unpacking and forced cleanup) which together enable automatic leakage of user documents and hide execution traces — strongly indicative of malicious/backdoor intent even though no explicit reverse-shell payload is present.