ClawHub
Back to skill

Security audit

longbridge

Security checks across malware telemetry and agentic risk

Overview

This appears to be a legitimate LongBridge brokerage CLI, but it gives an agent sensitive account access and live trading capability with overly broad activation guidance and a documented confirmation bypass.

Install only if you intentionally want an agent to access your LongBridge brokerage data. Keep LONGBRIDGE_TRADE_ENABLED unset or false by default, avoid --yes/-y for live trades, use paper-trading or least-privilege credentials where possible, and avoid storing brokerage .env files in shared or untrusted project directories.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (9)

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill requires access to sensitive environment variables containing API credentials and an access token, but it does not declare permissions explicitly. This creates a transparency and governance gap: a caller may invoke a skill that can access trading credentials without the platform surfacing that capability clearly.

Vague Triggers

High
Confidence
96% confidence
Finding
The trigger description is extremely broad and includes casual phrases like asking to check a stock price, holdings, or place an order, causing the skill to activate on ordinary conversation. In this skill's context, unintended invocation is especially dangerous because it exposes account data and includes buy/sell/cancel functionality, increasing the chance of privacy-sensitive actions or accidental trade flows.

Credential Access

High
Category
Privilege Escalation
Content
profile 非空 + 文件不存在 → 抛 FileNotFoundError。
    已存在的环境变量不会被覆盖。
    """
    filename = f".{profile}.env" if profile else ".env"
    env_path: Path | None = None
    for base in [Path.cwd(), Path.home()]:
        candidate = base / filename
Confidence
90% confidence
Finding
.env"

Credential Access

High
Category
Privilege Escalation
Content
profile 非空 + 文件不存在 → 抛 FileNotFoundError。
    已存在的环境变量不会被覆盖。
    """
    filename = f".{profile}.env" if profile else ".env"
    env_path: Path | None = None
    for base in [Path.cwd(), Path.home()]:
        candidate = base / filename
Confidence
90% confidence
Finding
.env"

Unpinned Dependencies

Low
Category
Supply Chain
Content
longbridge
click>=8.0
rich>=13.0
Confidence
95% confidence
Finding
longbridge

Unpinned Dependencies

Low
Category
Supply Chain
Content
longbridge
click>=8.0
rich>=13.0
Confidence
98% confidence
Finding
click>=8.0

Unpinned Dependencies

Low
Category
Supply Chain
Content
longbridge
click>=8.0
rich>=13.0
Confidence
93% confidence
Finding
rich>=13.0

Known Vulnerable Dependency: click — 1 advisory(ies): CVE-2026-7246 (Pallets Click, versions 8.3.2 and below, contain a command injection vulnerabili)

High
Category
Supply Chain
Confidence
86% confidence
Finding
click

Known Vulnerable Dependency: click==8.0 — 1 advisory(ies): CVE-2026-7246 (Pallets Click, versions 8.3.2 and below, contain a command injection vulnerabili)

High
Category
Supply Chain
Confidence
88% confidence
Finding
click==8.0

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.