ClawHub
Back to skill

Security audit

Airtable Automation

Security checks for vulnerabilities and agentic risk

Overview

This Airtable automation skill is coherent, but it enables record and schema changes including deletes without clear confirmation or preview safeguards.

Install only if you are comfortable giving the connected Airtable account automation access through Rube MCP. Before using it on real bases, require the agent to show the target base, table, records, and count, and give explicit approval for updates, schema changes, and especially deletes or bulk deletes.

A.I.G

Vulnerability Patterns
  • 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
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly includes AIRTABLE_DELETE_RECORD and AIRTABLE_DELETE_MULTIPLE_RECORDS in its core workflow without any guidance to require explicit user confirmation, preview affected records, or warn about irreversible data loss. In an automation skill that can operate on production Airtable bases, omission of safety gates materially increases the risk of accidental or prompt-induced destructive actions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.