ClawHub
Back to skill

Security audit

bilibili-search

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Bilibili search connector that calls a local API, with no bundled executable code or hidden high-impact behavior found.

Before installing, verify the separate local FastAPI service you plan to run, because that backend is not included here and will control the browser automation. Expect the skill to send search keywords to a localhost service that searches Bilibili.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The OpenAPI title, description, summary, and parameter description are all written in Chinese, which imposes a specific language on users and integrators. There is no indication that the skill is region-specific or that an alternative language or opt-in exists, so this appears to violate the language/locale policy criterion.

Content

No source excerpt is available for this finding.

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