ClawHub
Back to skill

Security audit

Modjo AI

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a coherent Modjo AI connector, but its first-time setup tells users to execute an unverified remote installer script.

Review the first-time setup carefully before installing. Prefer installing the oo CLI from independently verified official documentation or a signed/package-manager source, and do not run the pipe-to-shell commands from an elevated shell unless you have verified the installer and trust the publisher.

A.I.G

Vulnerability Patterns
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • 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
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Findings (1)

T03 · Remote Payload Retrieval and Execution

Error
Location
SKILL.md:74
Finding

Unverified Remote Installer Download and Execution

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, lines 74–78
Vulnerability Type: Remote payload retrieval and execution
Risk Level: High

Vulnerable Code

bash
curl -fsSL https://cli.oomol.com/install.sh | bash    # macOS / Linux
powershell
irm https://cli.oomol.com/install.ps1 | iex           # Windows PowerShell

Technical Analysis

The installation instructions retrieve mutable scripts from cli.oomol.com and immediately execute their contents using Bash or PowerShell. Neither command pins a specific installer version nor performs cryptographic signature or checksum verification. The user is also given no opportunity to inspect the downloaded content before execution.

Although the download domain appears related to the declared OOMOL service, the repository contains no evidence establishing the integrity or future behavior of these remote scripts. The effective executable payload can change after the Skill has been reviewed. Compromise of the download domain, hosting infrastructure, DNS resolution, TLS termination, or installer publishing pipeline could therefore turn these instructions into an arbitrary-code delivery channel.

This installation behavior is only presented as a fallback when the oo command is unavailable. It is not required for ordinary connector operations and exceeds the minimum privileges needed for the Skill's declared read-only Modjo AI functionality.

Attack Path

  1. A user or agent attempts to use the Skill on a system where the oo CLI is unavailable.
  2. The first-time setup instructions direct the user to run the applicable installation command.
  3. The command retrieves the current remote installer from cli.oomol.com.
  4. The response body is passed directly to Bash or PowerShell without integrity verification or review.
  5. If the remote delivery path or publishing infrastructure is compromised, attacker-controlled commands execute with the privile ...[truncated 909 chars]
Remediation
View remediation

Remediation Suggestions

  1. Remove direct curl | bash and irm | iex installation patterns.
  2. Prefer a trusted platform package manager or a version-pinned release from a verifiable official repository.
  3. Download the installer to a local file rather than piping it directly into a command interpreter.
  4. Publish and verify a cryptographic signature or strong checksum obtained through an independently protected channel.
  5. Allow the installer contents to be inspected before execution.
  6. Require explicit user approval before installing software or executing any downloaded script.
  7. Run installation with ordinary user privileges unless a documented operation strictly requires elevation.
  8. Document the exact release version, expected checksum, publisher identity, destination paths, and permissions required by the installer.
  9. Keep installation outside normal Skill execution. If the CLI is missing, report the condition and direct the user to independently verified installation documentation rather than executing the installer automatically.

SkillSpector

Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

External Script Fetching

High
Category
Supply Chain
Confidence
97% confidence
Finding

The skill instructs users to install software via curl ... | bash, which downloads and immediately executes a remote script without verification. If the install endpoint, network path, or hosting account is compromised, this becomes a direct remote code execution path on the user's machine.

Content

Scanner excerpt · SKILL.md (reported line 74)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The description says to use this skill for "ANY Modjo AI request" and "Whenever a task involves Modjo AI," which is an expansive activation condition without scope boundaries or exclusions. This can overlap with many ordinary requests that merely mention Modjo AI, making invocation criteria ambiguous.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.