ClawHub
Back to skill

Security audit

ClawEmail Admin

Security checks for vulnerabilities and agentic risk

Overview

This skill is mostly coherent for administering ClawEmail Google Workspace accounts, but it exposes sensitive credentials and permanent account deletion without enough built-in handling safeguards.

Review this skill before installing if the agent will have a real CLAWEMAIL_API_KEY. Treat returned passwords, OAuth links, and credentials JSON as secrets, avoid exposing them in chat or logs, and require explicit confirmation before any suspend, unsuspend, or delete action, especially deletion.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill provisions real Google Workspace accounts and returns highly sensitive credentials, including a one-time password and OAuth onboarding link, but it does not prominently warn that these secrets must be handled securely or not exposed in logs, chat history, or downstream tools. In an agent setting, that omission increases the chance of accidental credential disclosure and unauthorized access to email, Drive, Calendar, and other Workspace data.

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 · SKILL.md (reported line 29)May include surrounding context.

Before creating an account, always check if the prefix is available:

bash
curl -s https://clawemail.com/check/DESIRED_PREFIX

Response when available:

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill exposes a permanent delete operation for a Workspace account and all associated data without any explicit caution, confirmation, or recovery warning. In an agent-driven workflow, this creates a material risk of accidental or ambiguous destructive actions leading to irreversible loss of email and Workspace data.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.