ClawHub
Back to skill

Security audit

Native Airtable

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed, read-only Airtable helper that uses the user's Airtable token only to call Airtable's own API.

Install only if you are comfortable granting an Airtable PAT. Scope the token to read-only permissions and only the bases you want the agent to access, because command output can include Airtable record contents.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 84)May include surrounding context.

md
- Free plan: unlimited bases, 1,000 records per base. API reads work on free.
- Base IDs start with `app`, record IDs start with `rec`.
- Table names are case-sensitive and must match exactly. Use quotes if the name has spaces.
- Airtable deprecated old API keys in Feb 2024. Only Personal Access Tokens (PAT) work now.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding

The skill performs network access to Airtable and requires a sensitive environment variable, but it does not declare any explicit tool scope or permissions boundary. That omission increases the chance that an agent or reviewer will underestimate the skill's ability to access external data and credentials, which weakens least-privilege and auditability.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/airtable.py (reported line 13)May include surrounding context.

python
import urllib.parse
import urllib.request

BASE_URL = "https://api.airtable.com/v0"
META_URL = "https://api.airtable.com/v0/meta"

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/airtable.py (reported line 14)May include surrounding context.

python
import urllib.parse
import urllib.request

BASE_URL = "https://api.airtable.com/v0"
META_URL = "https://api.airtable.com/v0/meta"

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

This code makes authenticated HTTP requests to Airtable using the user's token and returns record data, which may include sensitive business information. While the module docstring notes that it calls the Airtable API directly, there is no user-facing warning in the command help, comments near the data-fetching commands, or output messaging that records and metadata will be transmitted to Airtable and printed to stdout.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.