Security checks across malware telemetry and agentic risk
This appears to be a real workflow automation skill, but installed workflows can run local code, make network requests, send messages, and touch OpenClaw session files with limited containment.
Install only if you intend to run trusted workflow YAML. Treat workflows as code with your user permissions: review every script/code/http/message/subagent step before running, avoid using it with sensitive environment variables, and do not run third-party YAML unless you would also run its shell commands directly.
}
try:
return bool(eval(resolved_str, {"__builtins__": safe_builtins}, namespace))
except Exception:
return Falseexcept (ValueError, IndexError):
return None
elif hasattr(obj, k):
obj = getattr(obj, k)
else:
return None
return objcwd = ctx.resolve(step.get("cwd")) if step.get("cwd") else None
try:
result = subprocess.run(
command,
shell=True,
capture_output=True,old_stdout = sys.stdout
try:
sys.stdout = captured
exec(compile(code, "<openclaw-workflow-sandbox>", "exec"), namespace)
sys.stdout = old_stdout
# 优先使用 ctx_export() 的值，其次检查 namespace 中的 result 变量old_stdout = sys.stdout
try:
sys.stdout = captured
exec(compile(code, "<openclaw-workflow-sandbox>", "exec"), namespace)
sys.stdout = old_stdout
# 优先使用 ctx_export() 的值，其次检查 namespace 中的 result 变量66/66 vendors flagged this skill as clean.