ClawHub
Back to skill

Security audit

Car Buying Assistant

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent car-buying research assistant that writes local comparison reports and explicitly avoids payments, logins, and direct seller contact.

Before installing, expect the skill to create car-search reports under ~/Documents/CarSearch/ and to research public vehicle listings. Keep payment, banking, SIN, address, login, and seller-contact actions under your direct control, as the skill itself instructs.

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
  • Memory PoisoningPersistent Context Injection, Context Window Stuffing, Memory Manipulation
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Memory Manipulation

High
Category
Memory Poisoning
Confidence
80% confidence
Finding

Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.

Content

Scanner excerpt · SKILL.md (reported line 141)May include surrounding context.

md
- **Summary line:** `Year Make Model – $price – km – city – dealer/private`
- **Pros:** price vs market, mileage, features, condition notes.
- **Cons / risks:** high mileage, rust, unclear history, old tires, etc.
- **Rough value call:** `good deal`, `fair`, or `overpriced` based on research.
- **Confidence level** (low/medium/high) in the assessment.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding

The skill explicitly instructs the agent to create folders and write multiple report files under ~/Documents/CarSearch/, but it declares no explicit tool scope or allowed-tools/permissions metadata. That mismatch can cause the runtime to grant broader-than-necessary file access by default or leave access control ambiguous, increasing the risk of unintended reads/writes outside the intended workspace.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.