ClawHub
Back to skill

Security audit

车险方案对比台

Security checks for vulnerabilities and agentic risk

Overview

This is a simple car-insurance comparison guidance skill with no executable code, no hidden data access, and only minor trigger-breadth concerns.

Before installing, be aware that the skill may handle personal insurance context such as vehicle details, driving history, and claims history. Avoid sharing unnecessary identifiers, and verify final pricing, coverage, and legal obligations with the insurer or local official sources.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The trigger list uses broad, everyday phrases like car insurance comparison and claims topics without strong invocation constraints, which can cause the skill to activate in situations where a user is asking a general question rather than explicitly requesting this specific skill. This creates an overbroad prompt-matching surface that may route unrelated conversations into the skill unexpectedly, reducing reliability and potentially exposing user-provided insurance or personal context to the wrong workflow.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The natural-language examples include generic follow-up phrases such as asking to make the result shorter or turn content into a table, which are not uniquely tied to this skill. If used by an orchestrator or matcher as invocation examples, they can cause accidental activation during ordinary editing requests in unrelated contexts.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.