Security audit
Security checks across malware telemetry and agentic risk
This is a powerful but coherent skill-building tool with disclosed local file, install, scheduling, and Telegram approval behavior, and I found no hidden exfiltration or automatic destructive install path.
Install this only if you want an agent to generate and update skills, read OpenClaw learning/feedback files, and optionally use Telegram plus a macOS schedule. Start with plan modes, protect the Telegram bot token or approval secret, review generated candidates before approval, and choose output directories that do not contain unrelated work.
def run_json(command: list[str], check: bool = True) -> dict:
completed = subprocess.run(command, check=check, text=True, capture_output=True)
if not completed.stdout.strip():
return {
"status": "no-output",def run_text(command: list[str]) -> str:
completed = subprocess.run(command, check=True, text=True, capture_output=True)
return completed.stdout.strip()def run_eval(skill_dir: str, cases: str, skill: str, min_score: int) -> dict:
completed = subprocess.run(
[
sys.executable,
str(BASE_DIR / "run_replay_eval.py"),def run_child(command: list[str], json_mode: bool = False, check: bool = False) -> int:
completed = subprocess.run(command, text=True, capture_output=True)
if json_mode:
payload = {
"status": "ok" if completed.returncode == 0 else "failed",def git_status() -> dict:
if not (REPO_DIR / ".git").exists():
return {"available": False, "detail": "not running from a git checkout"}
head = subprocess.run(
["git", "rev-parse", "--short", "HEAD"],
cwd=REPO_DIR,
text=True,text=True,
capture_output=True,
)
status = subprocess.run(
["git", "status", "--porcelain=v2", "--branch"],
cwd=REPO_DIR,
text=True,checks = []
release_script = REPO_DIR / "tests" / "run_release_checks.py"
if release_script.exists():
completed = subprocess.run([sys.executable, str(release_script)], cwd=REPO_DIR, text=True, capture_output=True)
checks.append(
{
"name": "release-checks",}
)
else:
completed = subprocess.run(
[sys.executable, str(SCRIPT_DIR / "validate_skill_candidate.py"), str(SKILL_DIR), "--json"],
text=True,
capture_output=True,}
)
if not release_script.exists():
secret_scan = subprocess.run(
[sys.executable, str(SCRIPT_DIR / "security" / "scan_secrets.py"), "--root", str(SKILL_DIR), "--json"],
cwd=SKILL_DIR,
text=True,def run_json(command: list[str], check: bool = False) -> dict:
completed = subprocess.run(command, text=True, capture_output=True, check=check)
if not completed.stdout.strip():
return {"status": "no-output", "returncode": completed.returncode, "stderr": completed.stderr.strip()}
try:def launchctl(args: list[str]) -> dict:
completed = subprocess.run(["launchctl", *args], text=True, capture_output=True)
return {
"returncode": completed.returncode,
"stdout": completed.stdout.strip(),def get_json(token: str, method: str, params: dict) -> dict:
query = urllib.parse.urlencode(params)
with urllib.request.urlopen(f"{api_url(token, method)}?{query}", timeout=35) as response:
return json.loads(response.read().decode("utf-8"))method="POST",
)
try:
with urllib.request.urlopen(request, timeout=30) as response:
payload = json.loads(response.read().decode("utf-8"))
except Exception as exc:
return {"sent": False, "status": "send-error", "error": str(exc)}65/65 vendors flagged this skill as clean.
No suspicious patterns detected.