ClawHub
Back to skill

Security audit

Ip Screener

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrow research-and-scoring workflow for finding novels with adaptation potential, with no executable code, persistence, credential use, or hidden authority.

Before installing, expect the agent to perform web searches and cite recent public novel-platform data. Use explicit prompts about novel/IP adaptation screening to avoid accidental activation from broad phrases like 小说筛选.

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
93% confidence
Finding

The skill description includes broad trigger phrases such as “IP筛选”, “小说筛选”, and “IP评分” without clear scope limits, exclusions, or disambiguation. This can cause unintended activation in unrelated contexts, leading the agent to perform web searches and ranking tasks on loosely matched prompts, which increases the chance of prompt hijacking through retrieved content and unnecessary external data access.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.