ClawHub
Back to skill

Security audit

Member Complaint Agent

Security checks for vulnerabilities and agentic risk

Overview

This skill is a focused complaint-handling assistant that drafts structured Linear comments and does not include hidden execution, persistence, or data-exfiltration behavior.

Before installing, confirm that your support team wants Chinese default comment templates and that agents should only write to Linear when explicitly performing complaint handling. Review drafted customer replies before sending, especially for refunds, legal threats, privacy issues, or escalation cases.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Content
Do not fake metrics if the underlying issue list is incomplete.

## Output Rules

### Separate fact from judgment
Confidence
85% confidence
Finding
Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Natural-Language Policy Violations

Medium
Confidence
94% confidence
Finding
The skill hard-codes Chinese output structures for the two default Linear comments without asking for or adapting to the user's preferred language. In a customer-support workflow, this can cause incorrect or unusable responses, create operator confusion, and increase the chance that staff post the wrong-language draft directly to customers or internal systems.

Natural-Language Policy Violations

Medium
Confidence
93% confidence
Finding
The analysis and reply patterns are written as fixed Chinese output templates, including required headings and response text, with no indication that another language may be used based on user preference. This can violate language/locale policy when applied to users who have not opted into Chinese-language handling.

Static analysis

No suspicious patterns detected.