ClawHub
Back to skill

Security audit

Mailchannels Email Api

Security checks for vulnerabilities and agentic risk

Overview

The skill provides a coherent email and delivery-event integration, with disclosed credential use and optional setup steps that deserve care.

MailChannels receives the messages and recipient information you send. Protect the API key and verify any custom API destination. Limit webhook-triggered actions to delivery processing, and enforce signature, body-digest, freshness, and account validation before acting. Choose an appropriate retention period for raw events. Inspect the linked repositories directly or pin reviewed tooling before using the optional discovery command; external code and runtime hook enforcement were not audited.

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
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
80% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

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

md
Base URL: `${MAILCHANNELS_BASE_URL:-https://api.mailchannels.net/tx/v1}`
- Send: `POST /send`
- Send async: `POST /send-async`
- Webhook: `POST /webhook?endpoint=<url>`, `GET /webhook`, `DELETE /webhook`, `POST /webhook/validate`
- Public key: `GET /webhook/public-key?id=<keyid>`

## Sending Email

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 17)May include surrounding context.

md
- `MAILCHANNELS_ACCOUNT_ID` (aka `customer_handle`)

Optional:
- `MAILCHANNELS_BASE_URL` (default: `https://api.mailchannels.net/tx/v1`), `MAILCHANNELS_WEBHOOK_ENDPOINT_URL`

## Domain Lockdown (DNS)

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 26)May include surrounding context.

md
- Value: `v=mc1; auid=<YOUR_ACCOUNT_ID>`

## API Quick Reference
Base URL: `${MAILCHANNELS_BASE_URL:-https://api.mailchannels.net/tx/v1}`
- Send: `POST /send`
- Send async: `POST /send-async`
- Webhook: `POST /webhook?endpoint=<url>`, `GET /webhook`, `DELETE /webhook`, `POST /webhook/validate`

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
88% confidence
Finding

The documentation recommends running npx skills without pinning the CLI version, creating a supply-chain risk if the resolved package or a future release is compromised. Although this is an optional discovery command rather than an MCP server configuration, invoking it can execute downloaded code with the user's permissions; --list does not prevent CLI execution.

Content

No source excerpt is available for this finding.