Back to skill

Security audit

China Commerce Copilot

Security checks for vulnerabilities and agentic risk

Overview

This is a narrow routing skill that helps choose a China commerce shopping specialist and does not include code execution, data access, persistence, or hidden behavior.

Installers should understand that this skill is a router for China shopping and takeout workflows. It may be invoked for broad shopping questions, so consider tightening trigger wording or adding language-preference guidance if precise activation is important.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest description is written to activate on Chinese phrases only and frames the skill as a China-commerce copilot, but it does not state that language choice is optional. This can violate a language/locale policy when the skill implicitly constrains interaction to Chinese without offering the user an explicit language preference or opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The only example clarification questions are hard-coded in Chinese, which instructs downstream behavior toward a specific language. Because no opt-in or alternative language path is provided, this is a natural-language locale-policy concern under the stated rules.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
82% confidence
Finding

The default prompt describes activation for any "shopping or takeout request," which is a broad everyday category rather than a narrowly scoped invocation condition. The file does not provide explicit trigger phrases, exclusions, or negative examples to clarify when this skill should or should not be selected.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The router guidance is broad enough that the skill may activate for loosely related shopping questions without clear constraints on when to defer to a more specific skill. In an agent setting, overly permissive routing can cause misclassification of user intent, unnecessary invocation of downstream commerce skills, and reduced control over what actions or advice the system provides.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.