Security audit

Amazon Review Advisor

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Amazon review-analysis and response-advice helper, with no evidence of hidden data access, persistence, or destructive behavior.

Reasonable to install for manual Amazon review analysis and response drafting. Before using generated buyer-contact, refund, or review-request wording, verify it against current Amazon Seller policies, avoid pasting unnecessary personal data, and do not use it to pressure or reward customers for changing reviews. Expect Chinese-first output unless you ask for English.

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
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 (4)

Natural-Language Policy Violations

Medium

Confidence: 91% confidence
Finding: The document title and framing present the skill content primarily in Chinese, with English included only for some template sections and no statement that users may choose their preferred language. Under the policy, forcing a specific language without opt-in is a natural-language locale violation unless the regional constraint is explicit and justified.

Natural-Language Policy Violations

Medium

Confidence: 98% confidence
Finding: This code formats the user-facing report entirely in Chinese string literals, which forces a specific language on all users. The file does not provide any opt-in, configuration, or documented justification for this locale restriction.

Natural-Language Policy Violations

Low

Confidence: 84% confidence
Finding: The skill description prominently presents its core tagline in Chinese, and the README overall does not state that users may choose their preferred language for interaction. This can violate language/locale policy expectations when a skill imposes a language without explicit user opt-in or choice.

Vague Triggers

Low

Confidence: 88% confidence
Finding: This YAML manifest includes generic activation-like keywords such as "amazon," "seller tools," "customer feedback," and their Chinese equivalents without any explicit trigger constraints or exclusion conditions. In a manifest file, such broad terms can overlap with ordinary e-commerce discussion and make it unclear when the skill should activate versus when it should not.

Static analysis

No suspicious patterns detected.