Security audit
Security checks across malware telemetry and agentic risk
This skill does what it says, but it can turn local agent skills into broad network-callable automation with weak default scoping.
Install only in a trusted local or private network. Before running it, change expose_skills from ['*'] to a small explicit allowlist, bind to 127.0.0.1 unless remote access is required, enable HTTPS for any non-local use, keep API keys out of command-line arguments, disable public docs if exposed, and avoid using full-auto/high-capability executors for skills that can send messages, modify accounts, delete data, deploy code, or access secrets.
def _run_fix(cmd: str) -> tuple[bool, str]:
"""执行修复命令，返回 (成功, 输出)。"""
try:
result = subprocess.run(
cmd, shell=True, capture_output=True, text=True, timeout=120
)
out = (result.stdout + result.stderr).strip()# 2. 生成自签证书（一步到位）
try:
subprocess.run(
[
"openssl", "req", "-x509", "-new", "-nodes",
"-key", str(KEY_PATH),logger.debug(f"Session cleanup failed (non-critical): {e}")
try:
proc = subprocess.run(
cmd,
capture_output=True,
text=True,# --print：非交互模式输出结果后退出
# --bare：跳过所有插件和 hooks，减少启动时间（测实比不加 --bare 快 ~1s）
try:
proc = subprocess.run(
["claude", "--print", "--bare"],
input=prompt,
capture_output=True,# 通过 stdin 传入 prompt，避免命令行参数 ARG_MAX 限制
# --approval-mode full-auto 必须设置，否则 codex 在非 TTY 环境下会等待用户确认
try:
proc = subprocess.run(
["codex", "--approval-mode", "full-auto"],
input=prompt,
capture_output=True,logger.debug(f"Session cleanup failed (non-critical): {e}")
try:
proc = subprocess.run(
cmd,
capture_output=True,
text=True,VirusTotal findings are pending for this skill version.
No suspicious patterns detected.