openclaw-workflow
What this skill does
Workflow automation and execution with integration to OpenClaw Gateway, including execution of Python code in a sandboxed environment.
github/leoyeai - Dangerous Code Execution - 2.1k stars
Threat analysis
Skill info
pkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=openclaw-workflowAssessments (8)
Dangerous Code Execution
Dangerous Code Execution via skillspector
scripts/engine/context.py
return bool(eval(resolved_str, {"__builtins__": safe_builtins}, namespace))Dangerous Code Execution via skillspector
scripts/engine/nodes.py
result = subprocess.run(
command,
shell=True,
capture_output=True,
text=True,
timeout=timeout,
cwd=cwd,
env=Dangerous Code Execution via skillspector
scripts/engine/sandbox.py
return __builtins__.__import__(name, *args, **kwargs) if hasattr(__builtins__, '__import__') else __import__(name, *args, **kwargs)Dangerous Code Execution via skillspector
scripts/engine/sandbox.py
exec(compile(code, "<openclaw-workflow-sandbox>", "exec"), namespace)Dangerous Code Execution via skillspector
scripts/engine/sandbox.py
exec(compile(code, "<openclaw-workflow-sandbox>", "exec"), namespace)Dangerous Code Execution via skillspector
scripts/engine/sandbox.py
exec(compile(code, "<openclaw-workflow-sandbox>", "exec"), namespace)Dangerous Code Execution via skillspector
scripts/openclaw_workflow.py
os.execvp("streamlit", ["streamlit", "run", dashboard_path, "--server.port", str(port)])Tool Misuse
Tool Misuse via skillspector
scripts/engine/nodes.py
subprocess.run(
command,
shell=TrueBadge
Add the Anomity scan badge for openclaw-workflow to your README.
How Anomity governs this at runtime
Scan-time vetting tells you what a skill says it will do. Anomity's Endpoint Sensor sees what agents actually do: it discovers skills alongside every other AI artifact on the endpoint, and runtime governance can allow, deny, or log the tool calls a skill triggers. Policy violations route to your SIEM, Slack, email, or Jira, backed by a queryable 90-day audit trail.
Book a 30-minute demo to see your own skill inventory.
Methodology and disputes
Every skill is assessed by the Anomity Skill Intelligence engine against its public source; findings indicate risk patterns, not confirmed exploitation. Maintainer of openclaw-workflow? Report an issue or request a rescan.
