ClawHub
Back to skill

Security audit

InfoLobby

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a coherent InfoLobby connector, but its first-time setup tells the agent to run unverified remote installer scripts.

Review the setup commands carefully before installing. Prefer installing the oo CLI from independently verified OOMOL documentation or a package manager with publisher verification, and require explicit approval before running any installer, create, update, or delete action.

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:64
Finding

Unverified Remote Installation Scripts Executed Directly by Shells

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, lines 64–68
Vulnerability Type: Remote payload retrieval and execution
Risk Level: Critical

Complete Code Snippet

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 download scripts from external URLs and execute them immediately using bash or PowerShell's Invoke-Expression alias, iex. Neither flow pins a version, verifies a cryptographic checksum or signature, saves the script for inspection, nor confirms its contents with the user before execution.

This makes the effective code mutable after the Skill has been reviewed. HTTPS protects the connection in transit but does not protect users if the distribution server, publishing account, installation script, or related infrastructure is compromised. The referenced domain is consistent with the declared OOMOL integration, but that does not eliminate the remote-code-execution and supply-chain risk.

The behavior also exceeds the Skill's declared tool boundary of allowed-tools: [Bash(oo *)]: installing the CLI requires arbitrary shell or PowerShell execution rather than merely invoking an existing oo executable. The Skill's core InfoLobby functionality only requires an authenticated connector client; it does not inherently require direct execution of mutable installation scripts.

Attack Path

  1. The oo executable is absent, and an attempted connector operation fails with oo: command not found.
  2. The user or agent follows the first-time setup instructions.
  3. curl or Invoke-RestMethod retrieves the installation script currently served by the external endpoint.
  4. The downloaded response is passed directly to bash or iex without integrity verification or review.
  5. If the endpoint or publishing infrastruct ...[truncated 1073 chars]
Remediation
View remediation

Remediation Suggestions

  1. Remove both pipe-to-shell and Invoke-Expression installation commands from the Skill.
  2. Prefer an official package manager with a version-pinned package and verifiable publisher metadata.
  3. If script-based installation is unavoidable, download a versioned artifact to a local file rather than executing the response stream directly.
  4. Publish and verify a cryptographic checksum and, preferably, a signature rooted in a separately distributed trusted key.
  5. Display or otherwise make the downloaded artifact available for review before execution.
  6. Require explicit user approval before installing software or executing any installer.
  7. Keep runtime automation within the declared Bash(oo *) boundary. If installation is outside that boundary, direct the user to independently reviewed installation documentation rather than having the agent execute it.
  8. Document the expected installer version, source, required privileges, filesystem changes, and rollback procedure. Explicitly warn users not to run the installer with elevated privileges unless strictly required.

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
98% confidence
Finding

The skill instructs the agent to install software by piping a remotely fetched script directly into a shell (curl ... | bash). This is dangerous because it executes unverified code from the network immediately; if the distribution endpoint, transport, or upstream script is compromised, the host running the skill can be fully compromised.

Content

Scanner excerpt · SKILL.md (reported line 64)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

Line L03 says to use this skill for "ANY InfoLobby request," including all read, create, update, and delete operations. This activation scope is extremely broad and does not provide constraints or negative examples, increasing the risk of unintended invocation whenever InfoLobby is mentioned.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.