ClawHub
Back to skill

Security audit

Bilibili

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Bilibili public-page analysis skill with disclosed limits; the main caveat is broad routing language and optional login-state context.

Before installing, understand that this skill may guide an agent to browse and summarize public Bilibili pages. Keep requests specific, avoid using it for bulk scraping or downloads, and only rely on login state when you intentionally want personal-page information organized.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The description says the skill should be invoked whenever access or automation related to Bilibili is needed, which is an overly broad activation trigger. Broad routing can cause the agent to select this skill for loosely related requests, increasing the chance of unintended browsing or data extraction actions on a third-party site without sufficient user intent validation.

Content

No source excerpt is available for this finding.