Security audit

car-recommender

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese-language car recommendation skill with no executable code, permissions, persistence, or sensitive data access.

Before installing, expect a Chinese-oriented car shopping assistant that may trigger on broad car or budget-related phrases. Treat its prices, sales rankings, and model details as advisory and verify current information with official sources or local dealers before making a purchase decision.

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

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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 (3)

Natural-Language Policy Violations

Medium

Confidence: 92% confidence
Finding: The manifest description and the provided opening script are written as if the skill will operate in Chinese by default, with no indication that users may choose another language. This creates a natural-language locale policy concern because it imposes a specific language without documented opt-in or justified regional scope.

Vague Triggers

Medium

Confidence: 96% confidence
Finding: The trigger list includes very broad and common terms such as “车”, “预算”, and generic vehicle categories, which can cause the skill to activate in unrelated conversations. This increases the chance of unintended routing, context hijacking, or user confusion, especially in environments where multiple skills compete for activation.

Natural-Language Policy Violations

Low

Confidence: 79% confidence
Finding: The description is written as a Chinese-only assistant identity ("你的智能购车顾问") with no indication that users may choose another language or locale. Under the policy, a language constraint should either be optional for the user or explicitly documented and justified as region-specific.

Static analysis

No suspicious patterns detected.