Back to skill

Security audit

Longbridge

Security checks for vulnerabilities and agentic risk

Overview

The Longbridge features fit the stated purpose, but automatic setup executes unverified installation code without clear user control.

Review and install the CLI separately, and require approval before further installation or synchronization of agent skills. Limit the connected account to the read access you need; retrieved information can include balances, holdings, and order history through OOMOL. The remote installer, CLI implementation, and credential-storage behavior were not bundled for inspection.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (5)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The supplied command executes an external installer from an Oomol domain, with no visible Longbridge search or read functionality or established connection to the declared purpose. Executing installation code is a materially different capability, not merely an ordinary data-access implementation detail. The downloaded script was not supplied, so its further behavior cannot be determined.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
88% confidence
Finding

The supplied chunk only initiates login; it contains no Longbridge search or read operation and does not establish that oo accesses Longbridge. Authentication could support the declared functionality, but here it is the entire supplied behavior rather than an implementation step accompanying that functionality.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The command pipes a mutable remote script directly into Bash without inspecting it or verifying a pinned artifact; the PowerShell alternative has the same execution pattern. Compromise of the distribution endpoint or installer could therefore execute arbitrary code with the agent's local permissions, despite the legitimate dependency-setup context and HTTPS transport.

Content

Scanner excerpt · SKILL.md (reported line 134)May include surrounding context.

The setup workflow instructs the agent to execute remote installation scripts without warning the user about local system changes.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The missing-CLI fallback tells the agent to install software without first obtaining approval for local system changes. A read-oriented Longbridge request does not itself authorize executing an installer, which can modify files and configuration with the agent's operating-system permissions.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 155)May include surrounding context.

md
- **`OOMOL_INSUFFICIENT_CREDIT`** — OOMOL billing stop. Recharge at `https://console.oomol.com/billing/token-recharge` before retrying.

- **HTTP 402 without `OOMOL_INSUFFICIENT_CREDIT`** — the third-party account itself has no active plan or credit. Report the provider error message as is; do not ask the user to recharge OOMOL.

## Resources