ClawHub
Back to skill

Security audit

GTmetrix

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent GTmetrix connector, but its setup instructions include running an unverified remote installer script if the required CLI is missing.

Review the setup path before installing. This skill is reasonable for GTmetrix automation once oo is already installed and connected, but do not let an agent run the curl-to-bash or PowerShell installer automatically; prefer a verified installation method from the publisher and confirm any start_test payload because it changes GTmetrix account state.

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:69
Finding

Unverified Remote Installer Downloaded and Executed Directly

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, lines 69–73
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 installation instructions retrieve mutable scripts from cli.oomol.com and immediately pass them to Bash or PowerShell. They do not pin an installer version, validate a cryptographic checksum or publisher signature, save the script for inspection, or otherwise verify the downloaded payload before execution.

The remote scripts are not included in the audited project, so their effective behavior cannot be determined from the artifact. Although the hostname is consistent with the declared OOMOL service and installation is presented as a conditional first-time setup step, direct pipe-to-interpreter execution is not required for the Skill's declared GTmetrix functionality. It expands the trust boundary from the reviewed Skill to mutable, externally hosted code.

Attack Path

  1. The oo command is unavailable on the user's system.
  2. The Agent or user follows the first-time setup instructions in SKILL.md.
  3. curl or Invoke-RestMethod retrieves an installer from cli.oomol.com.
  4. The response body is passed directly to Bash or PowerShell without integrity verification or review.
  5. If the hosting infrastructure, publishing process, DNS path, TLS endpoint, or installer content has been compromised, attacker-controlled commands execute locally.
  6. Those commands can perform any operation permitted to the account that launched the interpreter.

Impact Assessment

Exploitation provides arbitrary command execution with the privileges of the invoking user. The potential scope includes reading or modifying user-accessible files, stealing locally available crede ...[truncated 549 chars]

Remediation
View remediation

Remediation Suggestions

  • Remove both pipe-to-interpreter installation commands from the Skill.
  • Prefer installation through a trusted operating-system package manager or an official repository that verifies signed packages.
  • Pin the CLI to an explicit reviewed version rather than retrieving an unversioned installer.
  • If a standalone installer is necessary, download it to a local file first and do not execute it automatically.
  • Publish expected SHA-256 hashes and verify the downloaded artifact before execution.
  • Require a verifiable publisher signature in addition to a checksum, because checksums hosted alongside a compromised installer do not provide an independent trust boundary.
  • Display the verified installer or its requested changes for review and obtain explicit user approval before execution.
  • Run installation with ordinary user privileges unless a specific, documented operation requires elevation.
  • Keep setup outside the normal Skill action path; the Skill should continue to assume that the CLI is preinstalled and should return a clear error when it is absent.

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 via 'curl ... | bash', which executes a remote script without prior verification, pinning, checksum validation, or package-signature checks. If the install endpoint, transport, or upstream distribution is compromised, this could lead to arbitrary code execution on the host running the skill.

Content

Scanner excerpt · SKILL.md (reported line 69)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

This manifest/markdown description defines activation in very broad terms that could overlap with many ordinary tasks mentioning GTmetrix, without specifying boundaries or negative examples. The lack of narrower scope or exclusion conditions increases the risk of unintended invocation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.