Security audit
Security checks across malware telemetry and agentic risk
This skill does what it advertises, but it handles server credentials and report destinations in ways that need human review before use.
Review before installing. Use only a restricted server account, prefer SSH keys over passwords, remove or parameterize the hard-coded group ID, confirm every upload/report destination, and avoid running the upload script until credential logging and shell command construction are fixed.
"""执行命令"""
print(f"执行: {cmd}")
try:
result = subprocess.run(cmd, shell=True, capture_output=True, text=True)
if result.returncode != 0:
print(f"错误: {result.stderr}")
return result.returncode == 065/65 vendors flagged this skill as clean.
No suspicious patterns detected.