Caveat verdict

longbridge-assistant

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

Accesses a real brokerage account (LongBridge Securities) with LONGBRIDGE_APP_KEY, LONGBRIDGE_APP_SECRET, and LONGBRIDGE_ACCESS_TOKEN to monitor up to 49 stock positions including portfolio values; while the skill states it is monitoring-only and not trading, providing a brokerage access token with portfolio read access constitutes elevated access worth flagging.

⚠ 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.

63
security
60
transparency
70
maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (2)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · SECRET="你的AppSecret

Pattern match low

pip3 install — installs Python packages at runtime

setup.sh · prose · downgraded · pip3 install

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class B). 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: LONGBRIDGE_APP_SECRET, LONGBRIDGE_ACCESS_TOKEN). Requires 1 system binary.

package_installcredential_access

Is this flag fair?

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