ClawHub
Back to skill

Security audit

Car Negotiator

Security checks for vulnerabilities and agentic risk

Overview

This car-negotiation skill is a straightforward research, calculation, and template aid with disclosed web use and a local calculator script.

Before relying on outputs, confirm the vehicle region, taxes, fees, incentives, and current pricing sources. The skill appears appropriate for negotiation preparation, but its example templates should be reviewed before sending to dealers.

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
Confidence
89% confidence
Finding
The description lists trigger examples such as "lease [model]" and "best price [vehicle]" without defining activation constraints or exclusions. These phrases are broad enough to plausibly match ordinary conversation, increasing the risk of unintended invocation.

Natural-Language Policy Violations

Low
Confidence
95% confidence
Finding
The phrase "ET/US default" imposes a specific regional default in the skill description, but does not indicate user choice or opt-in. This can violate language/locale policy expectations when users are outside the US or prefer another locale.

Static analysis

No suspicious patterns detected.