Back to skill

Security audit

Dune

Security checks for vulnerabilities and agentic risk

Overview

The Dune integration is coherent, but its setup fallback executes unverified downloaded code without a separate approval step.

Review the setup before installing. Preinstall a reviewed CLI version or require explicit approval before running its installer. Check its automatic skill synchronization settings. OOMOL will mediate your connected Dune access; the remote installer and hosted connector implementation were not verified.

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 (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The supplied code bootstraps software from Oomol rather than accessing or modifying Dune data. Nothing in the supplied chunk establishes this installation as a supporting dependency for Dune. The downloaded script's contents are not provided, so its further behavior cannot be assessed.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
99% confidence
Finding

Piping a remotely downloaded script directly into Bash executes mutable external content without verifying its integrity or reviewing its behavior. Compromise of the installer distribution could yield arbitrary code execution with the agent's local privileges; the PowerShell fallback has the same underlying risk, despite both URLs being relevant to the dependency.

Content

Scanner excerpt · SKILL.md (reported line 60)May include surrounding context.

The setup fallback instructs the agent to execute downloaded installation scripts without warning the user about remote code execution or system changes.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The fallback directs the agent to install software without obtaining approval for executing remote code or making local system changes. A missing CLI therefore expands an ordinary Dune request into a host-modifying operation; the conditional trigger limits exposure but does not establish user authorization.

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 81)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