抖音作品爬取

• Outcome: Review
• Latest audit: Aug 6, 2026 · 2:58 AM UTC
• Version: 1.0.3

Overview

The skill largely matches its Douyin data lookup purpose, but it needs Review because it uses a third-party API with broad triggers and prints part of the API key in command output.

Install only if you are comfortable sending the Douyin account names or IDs you query to RedFox and using a RedFox API key from your environment. Avoid sensitive or regulated targets, prefer precise Douyin IDs, and remove or patch the API-key-prefix logging before using this in shared terminals, CI logs, or agent transcripts.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (8)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 88% confidence
• Finding: The skill documentation indicates use of environment variables and outbound network access to a third-party API, but no corresponding permissions are declared. This can cause the agent or platform to invoke capabilities users and reviewers were not clearly informed about, reducing transparency around secret access and data egress.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The README states that queries are sent to an external data service and discusses API key handling, but it does not clearly warn users that account identifiers and query terms will be transmitted to a third-party provider. This can lead users to submit personal, sensitive, or regulated data without informed consent, creating privacy, compliance, and data-governance risk.

Vague Triggers

Medium

• Confidence: 85% confidence
• Finding: The activation guidance includes multiple broad natural-language triggers such as '查看抖音视频' and '抖音内容采集', which can match ordinary user requests and cause the skill to run when the user may only want discussion or analysis. Because the skill sends queries to an external data provider, unintended invocation can disclose queried account identifiers and trigger external data access without sufficiently explicit user intent.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The README explains API key setup and mentions a third-party provider, but it does not clearly warn end users that account nicknames/IDs they query will be transmitted to an external service for processing. This creates a transparency and privacy issue: users may submit personal or sensitive target identifiers without understanding that the data leaves the local agent environment.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The skill describes querying Douyin accounts but does not clearly warn users that supplied account names/IDs are transmitted to an external third-party API and that third-party platform data is fetched in response. This creates a transparency and privacy risk because users may not realize their inputs are being shared outside the local agent environment.

Missing User Warnings

Low

• Confidence: 86% confidence
• Finding: The documentation instructs users to configure an API key in an environment variable but does not include any warning about keeping the credential secret, avoiding hardcoding, or preventing accidental logging/sharing. Poor credential-handling guidance increases the chance of token exposure and unauthorized API use.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The workflow explicitly instructs use of an environment-sourced API key to send user-supplied Douyin identifiers to a third-party endpoint, but it does not require any user-facing disclosure or consent before transmitting that data. This creates a transparency and data-handling risk: users may not realize their input is being sent off-platform and that the skill relies on stored credentials to access an external service.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The script prints the first 8 characters of the REDFOX_API_KEY to stdout, which is a partial credential disclosure. Even partial secrets can aid fingerprinting, correlation across logs, or reduce brute-force/search space, and console output may be captured by CI logs, terminals, chat transcripts, or shared agent outputs. In this skill context, the tool is designed for external API access and may run in automated environments, which makes log exposure more likely.

VirusTotal

64/64 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.