Security checks across malware telemetry and agentic risk
The skill is a coherent automated development agent, but it gives AI agents broad command, file, cloud, and publishing authority without enough user approval or containment.
Install only if you are comfortable giving this skill access to run commands, modify project files, use GLM/Claude/Notion/GitHub credentials, and potentially publish generated code. Use private GitHub repos by default, disable auto-publish/daemon health exposure unless needed, run builds in a sandbox with a scrubbed environment, and avoid using it on repositories or prompts that contain secrets or proprietary code.
return {'success': False, 'output': 'Project not found'}
try:
result = subprocess.run(
['python3', '-m', 'unittest', 'discover', '-s', 'tests', '-v'],
cwd=self.project_path,
capture_output=True,return {'success': False, 'output': 'Project path does not exist'}
try:
result = subprocess.run(
['python3', '-m', 'unittest', 'discover', '-s', 'tests', '-v'],
cwd=self.project_path,
capture_output=True,"""
try:
result = subprocess.run([
'claude', '-p', prompt,
'--allowedTools', 'Edit,Write,Bash'
], cwd=str(project_path), capture_output=True, text=True,try:
# agent-browser로 GitHub Trending 접근
subprocess.run([
'agent-browser', 'open',
f'https://github.com/trending/{self.language}?since=daily'
], capture_output=True, timeout=30, check=False)def _push_to_github(self, project_path: Path, repo_url: str):
"""GitHub로 push"""
subprocess.run(['git', 'remote', 'add', 'origin', repo_url],
cwd=str(project_path), capture_output=True)
subprocess.run(['git', 'push', '-u', 'origin', 'main'],
cwd=str(project_path), capture_output=True)"""GitHub로 push"""
subprocess.run(['git', 'remote', 'add', 'origin', repo_url],
cwd=str(project_path), capture_output=True)
subprocess.run(['git', 'push', '-u', 'origin', 'main'],
cwd=str(project_path), capture_output=True)
def _create_release(self, project_path: Path, title: str, description: str):prompt = self._generate_development_prompt(project)
try:
result = subprocess.run([
'claude', '-p', prompt,
'--output-format', 'json',
'--allowedTools', 'Edit,Write,Bash'After fixing, run tests to verify."""
try:
result = subprocess.run([
'claude', '-p', prompt
], cwd=str(project_path), capture_output=True, text=True,
timeout=120, env={**os.environ,import os
try:
result = subprocess.run(
['python3', '-m', 'unittest', 'discover', '-s', 'tests', '-v'],
cwd=str(project_path),
capture_output=True,import subprocess
try:
result = subprocess.run(
command,
shell=True,
cwd=str(workspace),try:
logger.info("Running %s hook: %s", hook.value, cmd)
result = subprocess.run(
cmd,
shell=True,
cwd=str(workspace.path),logger.info("Running tests in %s", project_path)
try:
result = subprocess.run(
['python3', '-m', 'unittest', 'discover', '-s', 'tests', '-v'],
cwd=str(project_path),
capture_output=True,def run_specific(self, project_path: Path, test_file: str) -> Dict:
"""특정 테스트 파일만 실행"""
try:
result = subprocess.run(
['python3', '-m', 'unittest', test_file, '-v'],
cwd=str(project_path),
capture_output=True,try:
# pytest-cov로 커버리지 측정
result = subprocess.run(
['python3', '-m', 'pytest',
'--cov=.',
'--cov-report=json',# openclaw agent 명령 실행
try:
result = subprocess.run([
'openclaw', 'agent',
'--message', prompt,
'--json'prompt = self._generate_fix_prompt(project_idea, error)
try:
result = subprocess.run([
'openclaw', 'agent',
'--message', prompt
], capture_output=True, text=True, timeout=60)return {'success': False, 'output': 'Project not found'}
try:
result = subprocess.run(
['python3', '-m', 'unittest', 'discover', '-s', 'tests', '-v'],
cwd=self.project_path,
capture_output=True,try:
# unittest 실행
result = subprocess.run(
['python3', '-m', 'unittest', 'discover', '-s', 'tests', '-v'],
cwd=self.project_path,
capture_output=True,"""
try:
result = subprocess.run([
'claude', '-p', prompt,
'--allowedTools', 'Edit,Write,Bash'
], cwd=str(project_path), capture_output=True, text=True,}
)
with urllib.request.urlopen(req, timeout=30) as response:
result = json.loads(response.read().decode())
content = result['choices'][0]['message']['content']64/64 vendors flagged this skill as clean.