ClawHub
Back to skill

Security audit

Ghost

Security checks for vulnerabilities and agentic risk

Overview

The Ghost read operations fit the stated purpose, but automatic setup can execute unverified remote code on your computer.

Review the setup behavior before enabling this skill. Install a verified CLI release yourself and require approval before any downloaded installer runs. Connect only the intended Ghost account and consider OOMOL's credential handling and usage charges. The installer payloads and their exact system changes remain unverified; the reviewed artifact does not establish malicious intent.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied command performs no visible Ghost search or read operation. Instead, it executes an installer from a different service, introducing local code execution not disclosed by the description. Nothing in the supplied chunk establishes this installer as a supporting dependency for Ghost access. The remote script's contents and resulting system changes cannot be determined from this chunk.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
92% confidence
Finding

Authentication could support a Ghost integration, but the supplied chunk contains only a login command and establishes no connection to Ghost. Its demonstrated primary behavior is authentication, not the declared searching and reading of Ghost data.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The installation command executes a mutable remote script immediately, without version pinning or independent integrity verification; the PowerShell alternative has the same weakness. If the distribution endpoint or release infrastructure is compromised, attacker-controlled code could execute with the agent's local permissions and access files or credentials. Limiting installation to a missing-CLI error reduces exposure, but does not make automatic execution safe.

Content

Scanner excerpt · SKILL.md (reported line 63)May include surrounding context.

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 84)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