Caveat verdict

longport-quant-trader

fxm1618-longport-quant-trader

45
🟠 Risky
Significant risk patterns flagged — automated deep scan, not behavioral proof.

This skill executes real automated stock trades on Hong Kong and US markets every 5 minutes using the user's brokerage credentials, buying and selling securities without per-trade confirmation — genuine risk of unintended financial loss, though all network calls are to the legitimate LongPort brokerage API.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

20
security
80
transparency
90
maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (6)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · SECRET = "your_app_secret

Pattern match high

Accesses shell history/config

SETUP_GUIDE.md · code · ~/.zshrc

Pattern match medium

References webhook/callback URL

SKILL.md · code · webhook_url

Pattern match medium

subprocess execution — runs system commands from Python

lianghui_monitor.py · prose · downgraded · subprocess.run(

Pattern match low

Python os.getenv — reads environment variable

feishu_push.py · prose · downgraded · os.getenv(

Pattern match low

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?

Check another skill Browse the registry Auditing your own skills or configs? Use the API