Back to skill

Security audit

E-commerce AI Toolkit Pro

Security checks for vulnerabilities and agentic risk

Overview

This ecommerce prompt skill is mostly a simple template library, but it includes a review-request workflow that asks for positive reviews in exchange for gifts or coupons.

Install only if you are prepared to revise the review-request template before use. Remove any request for specifically positive reviews and any gifts, coupons, discounts, or benefits tied to leaving a review; use neutral, honest feedback requests that comply with each marketplace's rules.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The usage section says the skill activates whenever users have broad needs like writing descriptions, analyzing competitors, handling customer service, product research, ad copy, or sales analysis. These are expansive, common tasks without clear trigger phrases, constraints, or negative examples, so the invocation boundary is unclear and could cause unintended activation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The section title and prompt explicitly require '英文' content for review-request messages, but the document does not indicate that language selection is optional or based on user preference. This can violate language/locale policy because it forces a specific language rather than offering a choice.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The template explicitly instructs requesting positive reviews while offering a gift or coupon as an incentive. On major e-commerce platforms, incentivized positive reviews are commonly prohibited because they manipulate marketplace trust signals and can lead to account sanctions, listing suppression, or consumer deception. The surrounding note to follow platform rules does not neutralize the earlier concrete instruction, so the skill context makes this more dangerous by packaging a policy-violating tactic as a reusable workflow.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.