ClawHub
Back to skill

Security audit

B站热门新番推荐

Security checks for vulnerabilities and agentic risk

Overview

This is an instruction-only Bilibili anime recommendation skill that uses public web search and does not request local access, credentials, persistence, or account control.

Reasonable to install if you want Bilibili current-season anime recommendations. Be aware it may trigger for broad anime recommendation prompts, so clarify when you want recommendations outside Bilibili or outside currently airing shows.

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
Confidence
92% confidence
Finding
The trigger scope is broad enough to activate on generic anime recommendation requests, not just Bilibili seasonal-anime queries. That can cause incorrect skill selection, unnecessary web access, and responses that are overly specific to Bilibili when the user asked for broader recommendations, which is a real security/quality boundary issue for agent routing.

Static analysis

No suspicious patterns detected.