ClawHub
Back to skill

Security audit

BuiltWith

Security checks for vulnerabilities and agentic risk

Overview

This BuiltWith connector skill is coherent and mostly read-only, but needs review because its setup instructions execute remote installer scripts directly in a shell.

Review the setup path before installing. Use this skill for BuiltWith lookups only, and avoid running the documented remote installer commands unless you trust the OOMOL distribution path and have verified the installer through a safer channel.

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:59
Finding

Unverified Remote Installer Scripts Executed Directly by Shell

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, lines 59–63
Vulnerability Type: Remote payload retrieval and execution
Risk Level: Critical

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 first-time setup instructions download mutable scripts from cli.oomol.com and immediately execute them through Bash or PowerShell. Neither command pins a release version, verifies a cryptographic signature or checksum, nor saves the script for review before execution.

Although HTTPS provides transport protection, it does not establish that the retrieved script is the same script that existed when the Skill was audited. Compromise of the remote server, hosting account, domain, CDN, TLS termination infrastructure, or release process could cause these commands to execute attacker-controlled content.

Installing the required CLI may be legitimate, but piping a remote response directly into a shell exceeds the minimum assurance necessary for installation. A package-manager installation or a version-pinned, independently verified artifact would accomplish the declared functionality with materially lower supply-chain risk.

The rest of the reviewed Skill contains no local executable code. Its documented transfer of domain query payloads and results through the OOMOL connector is consistent with its declared BuiltWith integration; no separate hidden exfiltration mechanism was identified.

Attack Path

  1. An attacker compromises cli.oomol.com, its hosting infrastructure, deployment credentials, CDN, or installer publication process.
  2. The attacker replaces either install.sh or install.ps1 with a malicious payload.
  3. The oo command is unavailable, causing the documented first-time setup path to become relevant.
  4. A user or Agent runs the provided installation command.
  5. Bash or PowerShell executes ...[truncated 1046 chars]
Remediation
View remediation

Remediation Suggestions

  1. Remove the direct curl | bash and irm | iex installation instructions.
  2. Prefer installation through a reputable platform package manager with a version-pinned package.
  3. If standalone installers are necessary:
    • Pin an immutable release version and artifact URL.
    • Download the artifact to a local file rather than piping it into a shell.
    • Publish and verify a SHA-256 or stronger digest through an independent trusted channel.
    • Prefer cryptographic signature verification using a documented release-signing key.
    • Allow the user to inspect the downloaded script before execution.
  4. Require explicit user approval before downloading or executing installation code.
  5. Run the installer without administrator or root privileges unless a documented operation strictly requires elevation.
  6. Document the files, permissions, network destinations, and configuration changes made by the installer.
  7. Consider directing users to a reviewed installation guide rather than instructing an Agent to execute remote installation code automatically.

A safer Unix-like workflow would resemble:

bash
curl -fLo oo-install.sh "https://trusted.example/releases/vX.Y.Z/install.sh"
echo "<expected-sha256>  oo-install.sh" | sha256sum --check
less oo-install.sh
bash oo-install.sh

The equivalent PowerShell workflow should download a version-pinned artifact with Invoke-WebRequest, verify its Authenticode signature or published checksum, and execute it only after explicit approval.

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 recommends installing the CLI via a remote script piped directly to a shell, which executes unverified code from the network without prior inspection. If the install endpoint, transport, or distribution pipeline were compromised, an agent or user following this guidance could execute attacker-controlled code on the host.

Content

Scanner excerpt · SKILL.md (reported line 59)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The manifest description uses an extremely broad activation condition: "Use this skill for ANY BuiltWith request" and "Whenever a task involves BuiltWith." In a markdown/manifest context, this lacks boundaries or negative examples and can overlap with many ordinary mentions of BuiltWith rather than clearly scoped invocation criteria.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.