ClawHub
Back to skill

Security audit

Mailboxlayer

Security checks for vulnerabilities and agentic risk

Overview

This Mailboxlayer skill mostly matches its stated purpose, but its setup guidance can run unverified internet installer scripts on the user's machine.

Review the setup path before installing. Prefer installing the oo CLI through a verified package or documented release process, and do not let an agent run the curl-to-bash or PowerShell iex installer automatically. Once the CLI and Mailboxlayer connection are already set up, the documented check_email workflow is narrow and purpose-aligned.

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:55
Finding

Unverified Remote Installer Scripts Executed Directly by Shells

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, lines 55-59
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 pass content retrieved from a remote server directly to bash or PowerShell's Invoke-Expression alias, iex. The downloaded scripts are neither pinned to a reviewed version nor verified with a cryptographic signature or expected checksum before execution.

Consequently, the effective code can change after the Skill has been audited. Compromise of the hosting service, publishing account, domain, DNS resolution, or relevant TLS trust infrastructure could cause attacker-controlled commands to execute. Even without infrastructure compromise, an upstream script update would execute without local review.

Installing the CLI is only a conditional setup operation and is not necessary to the core task of validating an email address when the CLI is already installed. Automatically executing a mutable remote installer therefore exceeds the minimum privileges needed for the declared Mailboxlayer functionality.

Attack Path

  1. The oo CLI is unavailable, causing the documented first-time setup fallback to be used.
  2. The user or agent runs the applicable installation command.
  3. curl or irm retrieves a mutable script from cli.oomol.com.
  4. An attacker who controls or has compromised the delivered response inserts arbitrary shell commands.
  5. The pipe to bash or invocation through iex executes those commands immediately under the invoking user's account.
  6. The payload can access resources available to that account and may retrieve additional payloads, modify files, or establish persistence.

Impact Assessment

Successful exploi ...[truncated 626 chars]

Remediation
View remediation

Remediation Suggestions

  1. Remove all direct curl | bash and irm | iex installation instructions.
  2. Distribute the CLI through a reputable platform package manager or a pinned release artifact.
  3. Pin installation instructions to a specific, reviewed CLI version rather than a mutable generic installer URL.
  4. Publish cryptographic checksums and signed release manifests through a separately protected channel.
  5. Download the artifact to a local file, verify its signature and checksum, and only then execute or install it.
  6. Display the verified artifact and intended installation effects to the user and obtain explicit approval before execution.
  7. Run installation with ordinary user privileges unless a narrowly defined operation demonstrably requires elevation.
  8. Keep software installation outside automated Skill execution; when the CLI is missing, return safe manual setup guidance instead of autonomously installing it.

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 the CLI via a curl ... | bash pattern, which executes remote code directly from the network without verification, pinning, or integrity checks. If the hosting endpoint, transport, or supply chain is compromised, this can result in arbitrary code execution on the user's machine.

Content

Scanner excerpt · SKILL.md (reported line 55)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The description says to use this skill for ANY Mailboxlayer request, which is an overly broad trigger that can cause the agent to invoke the skill in situations where direct handling or a narrower workflow would be more appropriate. In an agent ecosystem, this can lead to unintended delegation, expanded attack surface, and execution of connector-backed actions based on loose keyword matching rather than precise user intent.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.