Mcdonald - 麦当劳助手

ReviewAudited by ClawScan on May 1, 2026.

Overview

This instruction-only McDonald’s helper is purpose-aligned, but it uses an API token and curl calls that can read or claim coupons in the user’s account.

Before installing, verify that https://mcp.mcd.cn is the endpoint you intend to use, keep MCD_TOKEN private, and approve any coupon-claiming action only when you actually want the agent to change your account’s coupons.

Findings (4)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

Low

#ASI02: Tool Misuse and Exploitation

What this means

If the user asks for one-click coupon claiming, the agent may modify the user’s McDonald’s coupon account by claiming coupons.

Why it was flagged

The skill documents an account-changing tool that claims all available coupons. This fits the coupon-assistant purpose and is tied to explicit trigger phrases, but it still changes account state.

Skill content

### 2. 一键领取优惠券 (auto-bind-coupons)

自动领取所有可用优惠券到账户。

Recommendation

Confirm account-changing actions before running them, especially commands that claim all available coupons.

Medium

#ASI03: Identity and Privilege Abuse

What this means

Anyone or any tool with the token could potentially access coupon-related account functions available through the MCP service.

Why it was flagged

The skill requires a bearer token for account-specific MCP calls. This is expected for the stated service, but the token grants delegated access and is not declared in the registry requirements.

Skill content

用户需要在 MCP 官网注册并获取 API Token：
- 访问 https://mcp.mcd.cn 获取 Token
- 设置环境变量 `MCD_TOKEN`

Recommendation

Only use a token obtained from a trusted official source, keep it private, and rotate or revoke it if it may have been exposed.

Low

#ASI07: Insecure Inter-Agent Communication

What this means

If the endpoint is changed to an untrusted server, the user’s token could be sent outside the intended service.

Why it was flagged

The authorization token is sent to a configurable remote MCP endpoint. This is normal for the integration, but an untrusted MCD_MCP_URL would receive the token.

Skill content

MCD_URL="${MCD_MCP_URL:-https://mcp.mcd.cn}"
MCD_AUTH="Authorization: Bearer ${MCD_TOKEN:-<YOUR_TOKEN>}"

Recommendation

Leave MCD_MCP_URL at the trusted default unless you intentionally use a verified alternative endpoint.

Info

#ASI04: Agentic Supply Chain Vulnerabilities

What this means

Users have less provenance information to verify who maintains the skill or service instructions.

Why it was flagged

The registry metadata does not provide a source repository or homepage, while the skill relies on an external MCP service and token setup.

Skill content

Source: unknown
Homepage: none

Recommendation

Verify the skill publisher and MCP endpoint independently before providing an account token.