Back to skill

Security audit

Market Order Tracker

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed order-tracking playbook with customer notification templates, not an executable or hidden-access skill.

Installers should treat this as a business workflow template. Before using its automated notification examples, confirm the customer’s preferred channel, verify contact details, avoid unnecessary sensitive details in messages, and review attachments before sending.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill promotes automatic customer notifications over email, WhatsApp, and SMS and includes examples that transmit customer names, phone numbers, order numbers, shipment details, and documents. Without guardrails on consent, data minimization, channel approval, redaction, or secure handling of attachments, the automation could leak sensitive commercial and personal data to the wrong recipient or through insecure third-party channels.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill name, description, and tags are entirely in Chinese, which indicates a fixed language presentation with no mention of user language choice or locale scope. Under the policy, language constraints should either be optional for the user or explicitly documented as justified for a region-specific use case.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The file's communication section provides only English phrases for customer notifications and follow-ups, while the rest of the document is written in Chinese. This can be read as prescribing a specific output language for customer communications without user opt-in or a documented business/region-specific justification, which matches the language/locale policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The skill presents customer-facing notification templates in English while the surrounding skill is authored in Chinese, implying a default outbound language choice for users and customers. There is no statement that users can select the communication language or that English is required for a specific regional or compliance reason.

Content

No source excerpt is available for this finding.