ClawHub
Back to skill

Security audit

Airtable

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly coherent for Airtable work, but its setup instructions include direct execution of remote installer scripts without an explicit safety gate.

Review this skill before installing. Its Airtable operations are clearly described, but avoid letting an agent run the remote installer commands automatically; install the oo CLI only from a trusted, verified source and confirm any Airtable write or delete payload before execution.

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:68
Finding

Unverified Remote Installer Scripts Executed Directly

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, lines 68–72
Vulnerability Type: Remote payload retrieval and execution
Risk Level: Critical

Vulnerable code:

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 setup instructions download mutable scripts from an external server and immediately execute their contents through Bash or PowerShell. Neither command pins a release, verifies a cryptographic checksum or signature, nor provides an inspection step before execution. Consequently, the effective code executed by the Skill can change after the reviewed SKILL.md file has been published.

The installer domain is consistent with the stated OOMOL CLI provider, and installation is only recommended when the oo command is unavailable. Nevertheless, directly executing an unverified network response exceeds the minimum privileges and trust required to explain how to install the connector. A compromised vendor server, distribution infrastructure, DNS/TLS path, or installer could convert this documented setup action into arbitrary local code execution.

No evidence in the reviewed project establishes that the current remote scripts are malicious. The vulnerability is the unsafe execution mechanism and its dependence on mutable, remotely controlled content.

Attack Path

  1. The oo CLI is absent, causing an Airtable operation to fail with oo: command not found.
  2. The Agent or user follows the first-time setup instructions in SKILL.md.
  3. The command retrieves install.sh or install.ps1 from the external OOMOL endpoint.
  4. A compromised or maliciously modified endpoint returns attacker-controlled script content.
  5. Bash or PowerShell executes the response immediately, without integrity validation or prior review.
  6. The payload performs arbitrar ...[truncated 913 chars]
Remediation
View remediation

Remediation Suggestions

  1. Remove the curl | bash and Invoke-RestMethod | Invoke-Expression installation patterns.
  2. Direct users to an official, authenticated package manager or a version-pinned release artifact.
  3. Download the installer or binary to a local file without executing it automatically.
  4. Publish and require verification of a cryptographic checksum and, preferably, a signature tied to a trusted release key.
  5. Present the resolved version, source URL, checksum, and intended changes before requesting explicit user approval.
  6. Execute the verified artifact with ordinary user privileges; request elevated privileges only for narrowly identified installation steps.
  7. Avoid automatic installation by the Agent. On a missing CLI, stop and provide safe manual installation guidance.
  8. Document the files, directories, network endpoints, and permissions used by the installer so users can evaluate its scope.

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 recommends installing software via a remote script piped directly into a shell (curl ... | bash). This pattern allows arbitrary code execution if the hosting endpoint, transport, DNS, or supply chain is compromised, and the skill context makes it worse because it presents the command as a recovery step an agent may run automatically when the CLI is missing.

Content

Scanner excerpt · SKILL.md (reported line 68)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The description defines activation in extremely broad terms that overlap with many ordinary tasks involving Airtable, without clarifying boundaries or exclusions. This can cause unintended invocation because it provides no specific trigger phrases, constraints, or negative examples.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.