Walmart Review Checker

• Outcome: Review
• Latest audit: May 29, 2026 at 9:27 PM UTC
• Version:
  0.1.0

Overview

This is a local review-analysis skill, but its Walmart claims do not match the implementation and its hidden HTML report generator can render untrusted review text unsafely.

Install only after reviewing the package source. Treat the analysis as a generic/Amazon-style heuristic rather than a Walmart-specific authenticity check, avoid opening generated HTML reports from untrusted review data, and prefer plain text output unless the HTML rendering is fixed with proper escaping or textContent-based rendering.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration

Findings (6)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 77% confidence
• Finding: The skill advertises no declared permissions, yet the static analysis indicates file-write capability. Undeclared write behavior reduces transparency and can mislead users about what the skill does, which is dangerous because even seemingly benign report generation can overwrite files, drop unexpected artifacts, or be abused in chained attacks if paths are influenced by input.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 91% confidence
• Finding: The skill's documented Walmart-specific purpose does not match the reported behavior, which includes Amazon-specific analysis, ASIN usage, generic verified-purchase logic, and undocumented HTML report generation with Chart.js and file output. This mismatch is security-relevant because users may grant trust based on the stated scope while the skill performs broader or different actions than expected, including hidden output generation and potentially misleading analysis results.

Description-Behavior Mismatch

Medium

• Confidence: 94% confidence
• Finding: The file advertises itself as an Amazon review checker while the skill metadata claims Walmart-specific analysis. This kind of capability mismatch is a true security/trust issue because users may rely on outputs as if they were Walmart-specific when the logic is tuned to different platform signals, leading to materially misleading decisions.

Description-Behavior Mismatch

Medium

• Confidence: 97% confidence
• Finding: The analyzer data model and reporting are built around Amazon concepts such as ASIN and verified-purchase assumptions, not the Walmart-specific indicators promised by the skill description. In a security-sensitive agent ecosystem, this is dangerous because it creates deceptive functionality: downstream users or agents may treat unsupported Walmart fraud detections as authoritative.

Intent-Code Divergence

Low

• Confidence: 84% confidence
• Finding: The tool tells users that adding reviewer info will unlock account-profile analysis, but no such analysis exists. This is a real integrity issue because it can mislead operators into providing additional data under false pretenses and overestimating the comprehensiveness of the assessment.

Missing User Warnings

Medium

• Confidence: 98% confidence
• Finding: The script injects review.content and reasons directly into HTML via JavaScript template literals using innerHTML, with no escaping or sanitization. If review data contains HTML or script payloads, opening the generated report can trigger stored DOM XSS in the viewer's browser, which is especially relevant because review text is untrusted, user-derived input.

VirusTotal

64/64 vendors flagged this skill as clean.