ClawHub
Back to skill

Security audit

Givebutter

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent as a Givebutter read connector, but its setup includes unverified remote installer execution and broad routing that users should review before installing.

Install only if you trust OOMOL and are comfortable connecting your Givebutter account through it. Prefer a verified or package-manager install of the oo CLI instead of running the pipe-to-shell commands, and review any requested Givebutter action and payload before allowing changes to account data.

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:66
Finding

Unverified Remote Installation Scripts Are Executed Directly

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, lines 66–70
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 installation scripts from cli.oomol.com and pass them directly to a command interpreter. The Unix command pipes the response into Bash, while the Windows command uses Invoke-RestMethod and Invoke-Expression.

Neither command pins a release or expected digest, verifies a cryptographic signature, nor gives the user an opportunity to inspect the downloaded script before execution. Consequently, the effective code can change after the Skill package has been reviewed. HTTPS protects the connection in transit but does not address compromise of the hosting service, publisher account, DNS infrastructure, or upstream release process.

Although installation is only recommended after an oo: command not found error, installing a CLI does not inherently require immediate execution of unverified network content. This behavior therefore exceeds the minimum safe privileges necessary for the declared Givebutter read functionality.

Attack Path

  1. A Givebutter request causes the Agent to invoke the oo CLI.
  2. The command fails because oo is not installed.
  3. The Agent or user follows the documented first-time setup command.
  4. The command retrieves the current installation script from cli.oomol.com.
  5. If the hosting infrastructure, publisher account, or delivered script has been compromised, the attacker-controlled response is passed directly to Bash or PowerShell.
  6. The payload executes immediately with all privileges available to the invoking process.

Impact Assessment

A malicious installation script could execute ...[truncated 559 chars]

Remediation
View remediation

Remediation Suggestions

  1. Remove both pipe-to-shell installation commands from the Skill instructions.
  2. Direct users to an official package manager or a versioned release artifact from a verified publisher.
  3. Pin the CLI to a specific reviewed version rather than downloading an unversioned installation script.
  4. Publish and verify a SHA-256 digest and, preferably, a cryptographic signature before execution.
  5. Separate download and execution into distinct steps so the artifact can be inspected:
    • Download to a newly created, non-privileged location.
    • Verify the expected origin, version, digest, and signature.
    • Request explicit user approval before executing it.
  6. Avoid requesting administrator or root privileges unless a documented installation step strictly requires them.
  7. Prefer instructing the user to install the dependency manually rather than allowing the Agent to perform environment-changing installation automatically.
  8. Document the trust boundary and security implications of installing and using the OOMOL intermediary.

SkillSpector

Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (3)

Description-Behavior Mismatch

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The manifest and description frame the skill as intended for searching and reading data, but the body explicitly permits arbitrary connector actions and discusses write and destructive operations. This creates a capability mismatch that can cause downstream agents or reviewers to trust the skill as read-only when it may perform state-changing actions, increasing the risk of unintended modification of Givebutter data.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The skill instructs users to install software by piping a remotely fetched script directly into a shell (curl ... | bash), which is a well-known supply-chain and remote code execution risk. If the install endpoint, transport, or upstream distribution is compromised, arbitrary code will execute immediately on the host running the skill steps.

Content

Scanner excerpt · SKILL.md (reported line 66)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger text says to use this skill for ANY Givebutter request and instead of calling the API directly, which is an overly broad routing instruction. In agentic environments, such broad scope can cause the skill to be invoked for requests beyond safe read-only use, including sensitive or administrative workflows, especially given the connector can run arbitrary actions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.