ClawHub
Back to skill

Security audit

Ai Email No Human Interaction Needed

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent third-party receive-only email integration, but it encourages handling OTPs and password-reset links through an external mailbox without enough safety limits or warnings.

Review before installing. Use this only for disposable or low-risk signups unless you explicitly trust aiemailservice.com with the email contents, OTPs, and reset links involved. Avoid using it for important accounts, financial services, work accounts, or password recovery unless that third-party mailbox trust boundary is acceptable, and confirm before deleting any mailbox whose messages may still matter.

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 (6)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill explicitly promotes using a third-party receive-only mailbox for verification codes, password reset links, and inbound emails, but it does not warn that sensitive account-recovery material and message contents are being routed through an external service. This can lead users or agents to disclose secrets, OTPs, and reset links to infrastructure they may not control or trust, increasing account-takeover and privacy risk.

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 99)May include surrounding context.

javascript
// 1. Get API key
const { api_key } = await fetch('https://aiemailservice.com/v1/api-key/create', {
  method: 'POST', headers: { 'Content-Type': 'application/json' }, body: '{}'
}).then(r => r.json());

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 104)May include surrounding context.

md
}).then(r => r.json());

// 2. Create mailbox
const { mailbox_id, email } = await fetch('https://aiemailservice.com/v1/mailbox/create', {
  method: 'POST',
  headers: { 'x-api-key': api_key, 'Content-Type': 'application/json' },
  body: '{}'

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 128)May include surrounding context.

console.log('Verification code:', codes[0]?.codes[0]);

text

## Example: cURL

```bash
# Create API key

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 135)May include surrounding context.

md
KEY=$(curl -s -X POST https://aiemailservice.com/v1/api-key/create -H 'Content-Type: application/json' -d '{}' | jq -r '.api_key')

# Create mailbox
curl -s -X POST https://aiemailservice.com/v1/mailbox/create \
  -H "x-api-key: $KEY" -H 'Content-Type: application/json' -d '{}'

# Read messages

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The documented DELETE endpoint removes a mailbox and its messages, but the skill does not call out that this is destructive and may permanently erase verification emails, audit evidence, or recovery material. An agent following the documentation mechanically could delete needed data without user confirmation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.