ClawHub
Back to skill

Security audit

Bilibili Search

Security checks across malware telemetry and agentic risk

Overview

This appears to be a disclosed trend-fetching skill that uses public platform data, with a minor metadata transparency gap around network access.

Install only if you are comfortable with a skill making live requests to several public trend platforms. Use the scheduler only when you intentionally want a recurring local cron job, and remove it with the documented remove command when no longer needed.

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
94% confidence
Finding
The skill explicitly invokes a Python script that accesses Bilibili public endpoints, so it has network capability, yet the manifest only declares a binary requirement and does not declare network permission/capability. This creates a transparency and policy-enforcement gap: users or platforms may treat the skill as less privileged than it really is, reducing informed consent and weakening sandboxing or review controls.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.