Security audit

获取抖音博主主页视频列表

Security checks across malware telemetry and agentic risk

Overview

This skill appears to fetch Douyin video lists as advertised, but it sends a Douyin login cookie and API key to a third-party service without clear enough disclosure or safeguards.

Review before installing. Only use this if you trust the publisher and xueai.szzy.top with both your API key and a Douyin logged-in cookie. Prefer a separate low-risk Douyin session, rotate or remove the cookie after use, and avoid broad automatic activation until the skill clearly documents where credentials are sent and how they are protected.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands

Findings (7)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 86% confidence
Finding: The skill declares no permissions while its documentation clearly depends on sensitive environment variables, including an API key and an authenticated Douyin cookie. This creates a transparency and consent gap: users and reviewers may not realize the skill uses privileged credentials, increasing the chance of unintended credential exposure or unauthorized requests under the user's session.

Context-Inappropriate Capability

Medium

Confidence: 97% confidence
Finding: The skill reads sensitive credentials from environment variables, including a Douyin cookie and API key, and later forwards them to a third-party endpoint. This exceeds the stated purpose of simply fetching a user's video list and creates a clear credential-exfiltration risk if the external service is compromised, untrusted, or unnecessary.

Description-Behavior Mismatch

Medium

Confidence: 98% confidence
Finding: The implementation does not just retrieve Douyin videos; it proxies requests through an external API endpoint and includes authentication material in that request body. This mismatch between declared capability and actual behavior is dangerous because users may grant trust to a narrow function while the code silently broadens data exposure to another service.

Missing User Warnings

Medium

Confidence: 92% confidence
Finding: The skill states that the tool will automatically use the user's API key and Douyin cookie, but it does not warn that these are sensitive credentials tied to billing and an authenticated Douyin session. Automatic use of such secrets without explicit security messaging can lead users to provide high-value credentials without understanding the privacy, account, and session-hijacking risks.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The notes instruct users to obtain and reuse a live Douyin login cookie, effectively encouraging handling of a session credential that can grant account access if stolen or misused. Because cookies often represent authenticated browser sessions, documenting their collection and reuse without strong warnings materially increases the risk of credential theft, session replay, and privacy compromise.

Missing User Warnings

Medium

Confidence: 99% confidence
Finding: The code posts both the cookie and API key to an external HTTPS endpoint without any visible user-facing warning or consent. Sending reusable authentication tokens to a remote service can enable account/session misuse, data access beyond the intended operation, and downstream leakage if the service logs or stores request bodies.

Missing User Warnings

Low

Confidence: 91% confidence
Finding: Accessing sensitive environment variables is not inherently unsafe, but in this skill it is part of a flow that forwards those values externally while the file provides no disclosure about that behavior. In this context, undisclosed handling of credentials increases the chance of misuse and prevents informed consent by deployers.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.env_credential_access

Environment variable access combined with network send.

Critical

Code: suspicious.env_credential_access
Location: src/index.js:14