ClawHub
Back to skill

Security audit

bilibili-search

Security checks across malware telemetry and agentic risk

Overview

This skill coherently connects an agent to a user-run local Bilibili search service and shows no hidden or destructive behavior.

Install only if you intend to run and trust the local FastAPI/Playwright service it calls. Search keywords may be sent through that service to Bilibili, and headless browser activity can consume local resources.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.install_untrusted_source

Install source points to URL shortener or raw IP.

Warn
Code
suspicious.install_untrusted_source
Location
openapi.json:10