Security audit

ClawMart Customer Insights

Security checks for vulnerabilities and agentic risk

Overview

This skill is a plain Markdown guide for customer insight analysis, with sensitive customer-data use disclosed but no executable code or hidden behavior found.

Install only if you intend to analyze customer communications and business records. Before using it, confirm you are authorized to process the WeChat, email, and CRM data, limit inputs to what is necessary, and decide where any locally stored analysis should be kept and deleted.

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 (3)

Missing User Warnings

High

Confidence: 96% confidence
Finding: The skill is designed to process WeChat chats, email correspondence, and optional CRM data, but it provides no warning that these sources may contain personal, confidential, or regulated information. This is dangerous because users may expose sensitive customer communications to analysis and local storage without informed consent, minimization guidance, or handling restrictions.

Natural-Language Policy Violations

Medium

Confidence: 90% confidence
Finding: The skill instructions, examples, and output are entirely in Chinese, which imposes a language constraint in natural-language behavior. The file does not offer users a language option or explain that the skill is intentionally limited to a Chinese-language or region-specific context.

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The invocation examples are generic, everyday requests such as analyzing recent customer data or asking which customers are likely to convert. Broad triggers increase the chance of accidental activation in unrelated conversations, which can cause the skill to process sensitive business communications or CRM data without sufficiently deliberate user intent.

Static analysis

No suspicious patterns detected.