Game Account Valuation

• Outcome: Review
• Latest audit: May 28, 2026 · 2:01 AM UTC
• Version: 1.0.12

Overview

This skill appears purpose-built for game account valuation, but it sends account-linked and QR-login workflow data over plain HTTP with limited consent/privacy disclosure.

Review before installing. Only use this skill if you are comfortable sending game account identifiers, valuation attributes, and QR-login workflow data to the listed remote service. Prefer a version that uses HTTPS by default, asks before sending data or opening QR codes, explains retention/privacy handling, stores QR files in a private temporary directory, and removes or restricts raw debug backend commands.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (6)

Context-Inappropriate Capability

Medium

• Confidence: 93% confidence
• Finding: The script automatically opens whatever QR payload is returned by the backend, either as a remote URL or as a local file path generated under /tmp. For a valuation helper, causing the host to launch a browser or associated application based on untrusted server data exceeds the minimum necessary capability and could be abused for phishing, user tracking, or triggering dangerous URI handlers on the local system.

Context-Inappropriate Capability

Medium

• Confidence: 90% confidence
• Finding: The public query command lets callers submit arbitrary JSON directly to the backend /api/query endpoint, bypassing the narrower game-specific workflows and validations in the wrapper commands. That broadens the skill from a constrained valuation helper into a generic backend client, increasing the chance of unintended backend actions, access to unsupported operations, or data exfiltration if the service behavior changes.

Missing User Warnings

Medium

• Confidence: 92% confidence
• Finding: The README states that account-related attributes and identifiers are sent to a remote valuation service, but it does not clearly warn users that their data leaves the local environment or explain privacy implications. This is risky because users may provide game account identifiers, login-related metadata, and other potentially sensitive account attributes without informed consent, increasing exposure to third-party collection and misuse.

Missing User Warnings

High

• Confidence: 98% confidence
• Finding: The documented default backend uses plain HTTP, which exposes requests and responses to interception and tampering by anyone on the network path. Because this skill handles account identifiers and valuation workflow data, an attacker could eavesdrop on sensitive information or modify API responses, making the skill materially more dangerous in this context.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The skill collects and transmits sensitive account-related information—including game account identifiers, real-name status, anti-addiction status, and scan-based login/session data—to an external HTTP service without an explicit privacy notice or consent step. This is dangerous because users may unknowingly disclose personal or account-linked data to a third party over an insecure channel, creating privacy, account-security, and interception risks.

Missing User Warnings

Medium

• Confidence: 84% confidence
• Finding: QR code content is written to predictable files under /tmp, and the usage text does not clearly disclose that login-related artifacts will be stored on disk. On multi-user systems or environments with weak /tmp hygiene, these files may be discoverable by other processes or users, exposing login URLs, QR payloads, or other sensitive session material.

VirusTotal

VirusTotal engine telemetry is currently stale for this artifact.

Static analysis

No suspicious patterns detected.