Back to skill

Security audit

Amazon Aplus Generator

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only Amazon A+ copywriting skill whose behavior is disclosed and aligned with generating marketplace content.

Before installing, note that this skill is mainly documented in Chinese and may trigger on broad ecommerce copywriting prompts. Use explicit target marketplace and language instructions, and independently verify product claims, certifications, comparison data, and Amazon policy compliance before publishing.

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 (5)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The README presents all usage instructions and feature descriptions in Chinese, which imposes a specific language on users without indicating any option to choose another interface language. This is a natural-language policy concern because the skill documentation forces a locale/language experience rather than offering user choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The localization section maps each target language to a mandatory tone and emphasis, such as German being 'rigorous' and French being 'elegant, emotional, romantic.' This imposes locale-specific content behavior by default rather than offering it as an optional preference, which matches the policy concern about forcing language/locale behavior without user opt-in.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The keyword trigger set includes broad, common phrases such as "product description" and generic Amazon A+ terms that can match ordinary ecommerce-writing requests beyond the intended scope. This can cause the skill to activate unexpectedly, increasing the chance of workflow hijacking, user confusion, or unintended handling of prompts that should be routed to a different skill.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
82% confidence
Finding

Setting the manifest language to zh-CN without an explicit user opt-in can lead to outputs, prompts, or UX assumptions being presented in Chinese even when the user expects another language. In a multilingual ecommerce context, this may cause misrouting, misunderstanding of generated content, or accidental disclosure of business inputs to a locale-specific workflow the user did not intend to use.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The section '多语言本地化要点' gives prescriptive guidance for German, Japanese, French, Spanish, and Italian styles, but does not indicate that locale selection should be based on user choice or target-market opt-in. Per the policy, forcing a specific language or locale without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.