ClawHub
Back to skill

Security audit

bilibili-upload

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward Bilibili uploader that uses a user-specified file and metadata, with disclosed but sensitive saved login cookies.

Install this only on a trusted machine and only if you want an agent or script to upload videos to your Bilibili account. Review the video path, title, description, tags, and partition before running uploads, verify the biliup package source, and remove or revoke saved Bilibili login cookies when you no longer need automated uploading.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
Findings (2)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill mentions that login cookies are saved locally for future use, but does not present this as a prominent security warning or explain the sensitivity of those cookies. Reusable authentication cookies can grant account access for automated uploads, so users may unknowingly leave behind credentials on shared systems or in insecure storage, increasing risk of account takeover or unauthorized posting.

Missing User Warnings

Medium
Confidence
82% confidence
Finding
The skill sends a local video file plus user-supplied title, description, tags, and category metadata to an external platform via `biliup` without an explicit privacy or transmission warning at execution time. In a security review, this is a legitimate transparency/privacy issue because users may not realize exactly what data leaves the local system and under which authenticated account it is published.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.