Security audit
Security checks across malware telemetry and agentic risk
The skill is a disclosed stock research and AI4Trade integration with local records and confirmation-gated external actions; I found no artifact-backed deception or exfiltration.
Install only if you want this agent to access market data services, maintain local stock records, call optional local research backends, and use AI4Trade when you provide a token. Review any AI4Trade action carefully before allowing confirm=true, especially publishing, following, heartbeat/read-state changes, or point exchange.
def _run_research_backend(command: List[str], timeout_seconds: int) -> Dict[str, Any]:
"""Run a fixed local command without a shell and label its output untrusted."""
try:
completed = subprocess.run(
command,
capture_output=True,
text=True,env=environment, cwd=_ensure_quant_state_dir(), check=False,
)
else:
completed = subprocess.run(
[python, "-c", runner], capture_output=True, text=True, timeout=timeout_seconds,
env=environment, cwd=_ensure_quant_state_dir(), check=False,
)if bridge:
with bridge:
environment.update({"OPENAI_API_KEY": bridge.token, "OPENAI_BASE_URL": bridge.base_url})
completed = subprocess.run(
[python, "-c", runner], capture_output=True, text=True, timeout=timeout_seconds,
env=environment, cwd=_ensure_quant_state_dir(), check=False,
)self._respond(400, {"error": {"message": f"invalid request: {exc}"}})
return
try:
completed = subprocess.run(
[bridge.cli, "infer", "model", "run", "--gateway", "--json", "--prompt", prompt],
capture_output=True,
text=True,url = f"{safe_base_url}/api/v1/auth/login"
payload = json.dumps({"password": DSA_PASSWORD}).encode("utf-8")
req = urllib.request.Request(url, data=payload, headers={"Content-Type": "application/json"})
with urllib.request.urlopen(req, timeout=4) as res:
cookie_header = res.headers.get("Set-Cookie", "")
if "dsa_session=" in cookie_header:
for part in cookie_header.split(";"):self._respond(400, {"error": {"message": f"invalid request: {exc}"}})
return
try:
completed = subprocess.run(
[bridge.cli, "infer", "model", "run", "--gateway", "--json", "--prompt", prompt],
capture_output=True,
text=True,self._respond(400, {"error": {"message": f"invalid request: {exc}"}})
return
try:
completed = subprocess.run(
[bridge.cli, "infer", "model", "run", "--gateway", "--json", "--prompt", prompt],
capture_output=True,
text=True,def _run_research_backend(command: List[str], timeout_seconds: int) -> Dict[str, Any]:
"""Run a fixed local command without a shell and label its output untrusted."""
try:
completed = subprocess.run(
command,
capture_output=True,
text=True,if bridge:
with bridge:
environment.update({"OPENAI_API_KEY": bridge.token, "OPENAI_BASE_URL": bridge.base_url})
completed = subprocess.run(
[python, "-c", runner], capture_output=True, text=True, timeout=timeout_seconds,
env=environment, cwd=_ensure_quant_state_dir(), check=False,
)env=environment, cwd=_ensure_quant_state_dir(), check=False,
)
else:
completed = subprocess.run(
[python, "-c", runner], capture_output=True, text=True, timeout=timeout_seconds,
env=environment, cwd=_ensure_quant_state_dir(), check=False,
)65/65 vendors flagged this skill as clean.
No suspicious patterns detected.