视频号视频下载

• Outcome: Review
• Latest audit: Jul 24, 2026 · 8:04 AM UTC
• Version: 0.1.0

Overview

The skill appears to do what it says, but it needs Review because it sends user video links and a RedFox API key to a third-party API while promoting watermark-free/competitor downloads without clear privacy or authorization guidance.

Install only if you are comfortable sending WeChat share links to RedFox using your REDFOX_API_KEY, and use it only for videos you own or are authorized to download, reuse, or archive. Prefer a revocable/scoped API key and avoid submitting private or sensitive links.

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 (9)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 92% confidence
• Finding: The skill requires network access to a third-party API and reads an API key from environment or local configuration, but those capabilities are not explicitly declared. This creates a transparency and governance gap: users and platforms cannot accurately assess what sensitive resources the skill can access, increasing the risk of unintended secret use or unsanctioned outbound data transfer.

Vague Triggers

Medium

• Confidence: 89% confidence
• Finding: The README tells users to invoke the skill through unrestricted natural-language requests, which can cause the agent to apply the skill outside a narrowly intended context. In a capability that retrieves third-party video download links, vague triggering increases the chance of overuse, accidental invocation, or misuse for unauthorized content acquisition.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill explicitly markets downloading and archiving third-party WeChat Channels videos, including competitor content and watermark-free copies, without any warning about authorization, copyright, platform terms, or consent. This materially increases the risk of facilitating infringement, unauthorized redistribution, or policy-violating collection of content.

Vague Triggers

Medium

• Confidence: 86% confidence
• Finding: The README instructs users to invoke the skill through broad natural-language phrases rather than a tightly scoped command or explicit confirmation flow. That makes accidental or over-broad activation more likely, which can cause the agent to process arbitrary links and trigger external API usage when the user’s intent was ambiguous.

Missing User Warnings

Medium

• Confidence: 88% confidence
• Finding: The skill encourages downloading and reusing WeChat Channel videos, including for reposting, archiving competitor content, and derivative creation, but omits any warning about copyright, privacy, platform terms, or consent. That omission can facilitate misuse of third-party content and personal data, making harmful or non-compliant behavior more likely in normal use.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The workflow instructs the agent to send a user-provided WeChat video link and an API key to a third-party service, but it does not require any user-facing disclosure, consent, or data-handling warning. This creates a real privacy and trust risk because shared links may embed identifiers or sensitive content, and users are not informed that their data is being transmitted off-platform to redfox.hk.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The workflow instructs the agent to send a user-provided WeChat video link together with an API key to an external third-party endpoint, but it provides no user-facing notice, consent step, or data-handling warning. Even if the link seems innocuous, it may contain user-associated content or identifiers, and silent transmission to a third party creates privacy and trust risks.

Missing User Warnings

Medium

• Confidence: 86% confidence
• Finding: The script transmits user-supplied WeChat video links and a service API key to a third-party endpoint without clearly warning the user in the CLI usage or output. In this skill context, that means potentially sensitive or private share links are disclosed to an external service, which creates privacy, compliance, and trust risks even if the network behavior is functionally required.

External Transmission

Medium

• Category: Data Exfiltration

Content

payload = {"url": video_url, "source": "视频号视频下载-GitHub"}

    try:
        resp = requests.post(API_URL, headers=HEADERS, json=payload, timeout=REQUEST_TIMEOUT)
    except requests.exceptions.Timeout:
        return {"success": False, "reason": "请求超时，请稍后重试"}
    except requests.exceptions.ConnectionError:

• Confidence: 84% confidence
• Finding: requests.post(API_URL, headers=HEADERS, json=

VirusTotal

63/63 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.