ClawHub
Back to skill

Security audit

Bilibili Toolkit Free

Security checks across malware telemetry and agentic risk

Overview

This Bilibili skill mostly matches its stated purpose, but its broad trigger wording and file-writing download workflows need human review before install.

Review this skill before installing. Use it only for explicit Bilibili tasks, confirm any download/save action first, and run commands from a dedicated directory where unexpected output files are easy to inspect or remove. Do not provide Bilibili session credentials unless you specifically intend to use authenticated features and trust the implementation.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

High
Confidence
95% confidence
Finding
The trigger conditions are overly broad and mismatched to the skill’s actual Bilibili-focused functionality, mentioning generic data analysis, reporting, statistics, and visualization. In an agent ecosystem, this can cause the skill to be invoked for unrelated tasks, leading the agent to run networked commands or downloader actions unexpectedly and increasing the chance of unintended file writes or external requests.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill documents download and execution flows using `python main.py ... download` but does not clearly warn that these actions may execute local commands and write files to disk. In a tool-using agent, this omission can mislead users and orchestrators into treating the skill as low-risk, even though it can cause persistent local side effects and trigger network activity against external services.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.