T09 · Insecure Skill Coding Practices
Warning
- Location
SKILL.md:39- Finding
Identity-Bearing MCP Token Exposed Through Command-Line Arguments and Plaintext Configuration
- Content
View full analysis
- Remediation
View remediation
Security audit
麦当劳 MCP 点餐
Security checks for vulnerabilities and agentic risk
Overview
This skill is a coherent McDonald's China ordering integration, but users should handle the account token carefully because it enables account-linked actions.
Before installing, treat the MCP token like a password for your McDonald's account: do not paste it into shared chats or logs, restrict any config file that stores it, and revoke or rotate it if exposed. Confirm prices and order details before creating paid or points-redemption orders.
Vulnerability Patterns
- Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
- 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
Findings (1)
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 (2)
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The skill handles food ordering workflows that necessarily transmit sensitive user data such as delivery addresses, store selections, account-linked coupons, points balances, and order details to the McDonald's MCP service, but the referenced section does not clearly warn users about that exposure. Because the skill also asks users to supply an MCP token representing their member identity, missing disclosure increases the risk of users unknowingly sharing personal and account-linked data with a third-party service.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 76% confidence
- Finding
The skill description presents the primary instructions in Chinese while appending an English usage sentence, effectively imposing a default locale/language presentation without offering a user choice. The regional scope for mainland China is documented, but the language preference itself is not presented as optional or user-selectable.
- Content