ClawHub
Back to skill

Security audit

Customer Satisfaction Survey

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Chinese-language customer satisfaction survey/reporting guide with disclosed local report output and no bundled executable code, network access, persistence, or credential handling.

Install only if a Chinese-language customer satisfaction survey workflow is appropriate for your use. Before generating reports, confirm where files will be written and do not provide confidential customer data unless the surrounding environment is approved for that data.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
The file consistently specifies and presents the skill in Chinese, including the description, title, instructions, and outputs, with no indication that users may choose another language. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly justified, which is not present here.

Missing User Warnings

Low
Confidence
93% confidence
Finding
This markdown file documents a file-writing operation: `scripts/build_report.py` generates `.md` and `.txt` outputs, and line L085 states that without `--input` it uses a built-in sample and writes to the current directory by default. The description explains the behavior, but it does not include a user-facing warning or caution about automatic file creation or overwriting risk, which is relevant for a skill that affects the local filesystem.

Static analysis

No suspicious patterns detected.