Security audit

牛股王机游共振

Security checks across malware telemetry and agentic risk

Overview

The skill is a stock-screening helper, but it includes a hardcoded usertoken despite saying no API key is needed.

Review before installing. The skill is not destructive and does not request local credentials, but the publisher should remove or replace the hardcoded usertoken and rotate it if it is real. Users should avoid reusing that token and should verify the data source and investment disclaimer before relying on any stock-screening output.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Context-Inappropriate Capability

Medium

Confidence: 99% confidence
Finding: The skill embeds a concrete `usertoken` in a curl example, which is effectively account-linked access data and should be treated as a secret unless explicitly documented as a revoked/demo token. Publishing such a token in skill documentation can enable unauthorized API use, quota consumption, account attribution, or access to data/features beyond what an anonymous stock-screening example requires.

Missing User Warnings

Medium

Confidence: 98% confidence
Finding: The example presents a live-looking user token with no warning that it may be sensitive credential material. This normalizes unsafe handling of access data and increases the chance that users, downstream agents, or repositories will reuse, log, or redistribute credentials, leading to unauthorized access or abuse of the associated account.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.