Back to skill

Security audit

VIP

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Vipshop shopping assistant that can automate browsing and cart preparation but explicitly leaves payment and final order submission to the user.

Before installing, understand that this skill may use browser automation on Vipshop with your logged-in session to view cart details, apply coupons, select or confirm delivery information, and prepare an order preview. Keep payment and final order submission manual, review the cart/address/price yourself, and ask the agent to stay in manual guidance mode if you do not want account-based browser automation.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
95% confidence
Finding

The primary skill description is written as an unconditional Chinese-language instruction and does not indicate that users may choose another language. Under the policy, language constraints must be opt-in or clearly justified as region-specific; neither is stated here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The description specifies usage triggers entirely around Chinese shopping phrases and the rest of the skill heavily prescribes Chinese-language interaction patterns. There is no statement that the skill is China-specific by policy or that users may choose another language, which creates a natural-language locale policy concern.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 273)May include surrounding context.

md
- ❌ Recommend items with no stock
- ❌ Store user data persistently
- ❌ **Execute payment or final order submission**
- ❌ Guarantee inventory without checking

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The natural-language description is entirely in Chinese and presents the skill as a Chinese shopping assistant without offering any language or locale choice. This can violate language/locale policy when a skill implicitly constrains interaction to a specific language absent user opt-in or documented regional justification.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.