Back to skill

Security audit

Amazon Expansion Playbook

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language Amazon expansion reference skill with market, localization, tax, and compliance guidance, and it does not include executable code or hidden privileged behavior.

Before installing, be aware that the content is written in Chinese and some legal, tax, fee, and marketplace details may need independent verification for your current country, product category, and Amazon policy version.

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 (7)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill description and all user-facing instructions are written exclusively in Chinese, with no indication that users may choose another language or that the skill is intentionally limited to a Chinese-speaking audience. This creates a natural-language policy concern because it imposes a language constraint without opt-in or justification.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger list includes very broad, common phrases such as 'amazon expansion', 'international expansion', and '新市场', which are likely to appear in ordinary business conversations unrelated to an intentional invocation of this skill. This can cause the skill to activate unexpectedly, increasing the chance of context leakage, user confusion, or inappropriate routing to this skill instead of a more relevant one.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
81% confidence
Finding

The skill is written entirely in Chinese and presents prompts, commands context, and reply formatting only in Chinese, with no statement that users may choose another language. Under the policy, forcing a specific language without opt-in can be a natural-language policy violation unless the locale constraint is explicitly documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The description is entirely in Chinese and presents the skill as a general global expansion playbook, but there is no indication that Chinese is optional or that the skill is intended only for Chinese-speaking users. This can violate language/locale policy expectations when a skill implicitly forces a specific language without user opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

Lines L044-L045 use categorical language such as “日语必须,不接受英语,” which imposes a language requirement in natural language without presenting it as an optional user choice. Under the policy, forcing a specific language without opt-in is a locale/language policy violation unless clearly justified as a region-specific compliance constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This section requires multiple content types and customer service responses to be in Japanese, including “客服(日语回复),” with no indication of user choice or optionality. While some localization may be practical, the text presents a hard language constraint broadly rather than documenting a narrow justified exception.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

Lines L253-L257 prescribe that product titles, descriptions, manuals, and customer service must be in Spanish. Under the stated policy, forcing a specific language without user opt-in or an explicit documented justification is a natural-language policy violation.

Content

No source excerpt is available for this finding.