ClawAudit verdict
longport-quant-trader
The skill executes live stock buy and sell orders automatically every 5 minutes based on momentum/reversion thresholds without per-trade user confirmation, representing genuine elevated financial risk via autonomous real-money trading.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Permission integrity
package_install
Findings (6)
Possible hardcoded credential
SKILL.md · code · SECRET = "your_app_secret
Accesses shell history/config
SETUP_GUIDE.md · code · ~/.zshrc
References webhook/callback URL
SKILL.md · code · webhook_url
subprocess execution — runs system commands from Python
lianghui_monitor.py · prose · downgraded · subprocess.run(
Python os.getenv — reads environment variable
feishu_push.py · prose · downgraded · os.getenv(
Python httpx request — network access
get_openid_and_send.py · prose · downgraded · httpx.post(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
Requires 3 environment variables. (2 sensitive: LONGPORT_APP_SECRET, LONGPORT_ACCESS_TOKEN). Requires 1 system binary.
package_installnetwork_in Is this flag fair?
Thanks — recorded.