ClawHub
Back to skill

Security audit

抖音视频总结

Security checks across malware telemetry and agentic risk

Overview

This skill does what it says: it extracts a Douyin audio URL, sends it to a disclosed transcription service, and summarizes the transcript.

Install only if you are comfortable sending Douyin audio URLs, video metadata, and a service API key to calapi.ailuk.cn for transcription. The support service says it temporarily uploads audio as a public OSS object and passes it to Tencent Cloud, then deletes it, so avoid using this for private or sensitive videos unless you trust that service and its billing page.

SkillSpector

Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill invokes a Node.js script, consumes environment variables including an API key, and makes outbound network requests to a fixed third-party transcription service, yet no permissions are declared. This creates a mismatch between the skill's actual capabilities and its stated trust boundary, which can lead to over-privileged or non-transparent execution and exposure of sensitive data such as URLs, media metadata, and credentials.

VirusTotal

64/64 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
scripts/transcribe.js:9