ClawHub
Back to skill

Security audit

bilibili-watcher

Security checks across malware telemetry and agentic risk

Overview

This skill transparently runs a local helper with yt-dlp to fetch Bilibili subtitles, with no evidence of hidden data access, persistence, or destructive behavior.

Install this only if you are comfortable running a local Python script and installing yt-dlp. Use it for Bilibili links you intend to process, and review the yt-dlp package/version separately in sensitive environments.

SkillSpector

By NVIDIA
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
87% confidence
Finding
The skill invokes a shell command (`python3 ...` with an external tool dependency on `yt-dlp`) but does not declare any permissions for shell execution. This creates a permission-model gap: an agent or reviewer may underestimate the skill's ability to execute local commands and access network resources, which increases the chance of unsafe deployment or misuse.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.