Back to skill

Security audit

ShipStation

Security checks for vulnerabilities and agentic risk

Overview

Its ShipStation reads fit the stated purpose, but fallback setup lacks clear user approval for broader software and agent changes.

Review and approve CLI setup separately before allowing this skill to install software. Verify the installer or selected release, review or disable automatic skill synchronization, and grant only the ShipStation access needed. OOMOL mediates account access. The concerns are installation control and broader persistent effects; the inspected artifact does not establish malicious behavior, and the remote installers remain unverified.

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
98% confidence
Finding

The supplied command does not perform any visible ShipStation operation. It executes a third-party installer, and no connection is shown establishing this installation as a supporting requirement for the declared purpose. The remote script's contents and any additional effects cannot be determined from this chunk.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping a downloaded script directly into Bash executes mutable remote code without a pinned version or independent integrity verification. Compromise of the installer distribution path could enable arbitrary commands with the invoking user's privileges; the PowerShell installation alternative has the same underlying risk, although there is no evidence the endpoint is currently malicious.

Content

Scanner excerpt · SKILL.md (reported line 58)May include surrounding context.

The setup workflow executes remote installation scripts without warning about local system changes or remote-code execution.

Medium
Category
Output Handling
Confidence
93% confidence
Finding

A missing CLI triggers instructions to install software by executing remote scripts, without requiring explicit approval for local system changes. This expands a read-only ShipStation task into local code execution; the missing-command condition limits exposure, and the declared Bash(oo *) restriction may block execution if enforced strictly.

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 79)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