Security audit

Amazon Push Score

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Chinese-language Amazon listing scoring guide that asks for four user-provided metrics and does not install code, access accounts, or run external tools.

Install this if you want Chinese-language Amazon listing scoring guidance based on manually supplied metrics. Treat the score and benchmarks as operational advice rather than verified Amazon algorithm data, and be aware it may activate on broad Amazon CTR/CVR or ranking discussions.

A.I.G

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

SkillSpector

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 (6)

Tp2

High

Category: MCP Tool Poisoning
Confidence: 85% confidence
Finding: Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Tp2

High

Category: MCP Tool Poisoning
Confidence: 85% confidence
Finding: Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Tp2

High

Category: MCP Tool Poisoning
Confidence: 85% confidence
Finding: Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Natural-Language Policy Violations

Medium

Confidence: 89% confidence
Finding: The file instructs use based on Chinese-only phrases and the rest of the skill content is exclusively Chinese, which effectively forces a specific language/locale. Under the policy, locale or language constraints should either offer user opt-in or be clearly documented and justified as region-specific.

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The trigger list contains very broad ecommerce terms such as “A9算法”, “CTR优化”, and “亚马逊排名” that are likely to appear in normal conversations beyond the narrow intended use case. This can cause overbroad or unintended skill activation, which may route users into this skill when they did not explicitly request it, increasing the chance of irrelevant guidance or prompt-scope confusion.

Natural-Language Policy Violations

Low

Confidence: 88% confidence
Finding: All user-facing natural-language fields in the manifest, including the description and trigger phrases, are exclusively in Chinese. The file does not state that the skill is region-specific or offer any language/locale choice, which can conflict with a policy requiring user opt-in before enforcing a specific language.

Static analysis

No suspicious patterns detected.