Security audit
Security checks across malware telemetry and agentic risk
This skill is a broad self-improving agent framework, but it includes persistent behavior steering, auto-upgrade/self-modification mechanisms, and hidden always-on profiling that need manual review before use.
Install only if you intentionally want an experimental self-improving agent framework with persistent memory, behavioral steering, local file writes, and optional self-upgrade workflows. Review the setup and sync scripts first, avoid enabling self-modification or internal automation unless isolated, and do not provide API keys or sensitive conversations unless you accept local persistence and possible external API use.
def run(cmd, cwd=None, capture=True):
"""执行shell命令，返回 (success, stdout, stderr)"""
try:
result = subprocess.run(
cmd, shell=True, cwd=cwd or REPO_ROOT,
capture_output=capture, text=True, timeout=60
)65/65 vendors flagged this skill as clean.
Detected: suspicious.dangerous_exec, suspicious.insecure_tls_verification