ClawHub
Back to skill

Security audit

China Ecommerce Customer Service

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Chinese ecommerce customer-service script generator with no evidence of hidden access, persistence, command execution, or data exfiltration.

Installers should treat this as a China-market Chinese customer-service writing aid and manually review generated replies for platform rules and legal compliance. The included Python complaint-reply example may need fixing before reuse as executable code.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (5)

Natural-Language Policy Violations

Medium
Confidence
92% confidence
Finding
The description states the skill is a Chinese ecommerce customer-service script generator and the examples and notes indicate support for Chinese scripts only. This is a natural-language locale constraint presented as the default behavior, but the file does not offer the user a language choice or opt-in for Chinese output.

Intent-Code Divergence

Medium
Confidence
97% confidence
Finding
The method signature and docstring indicate `generate_complaint_reply(platform, issue_type, solution)` generates a complaint reply from those inputs, but the implementation formats the template using `details.get('issue', '这个问题')` even though no `details` parameter exists. This directly contradicts the documented usage and causes the code to fail rather than behave as the surrounding documentation suggests.

Scope Creep

Low
Category
Excessive Agency
Content
permit persons to whom the Software is furnished to do so.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED,
INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR
PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE
FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
Confidence
70% confidence
Finding
Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Natural-Language Policy Violations

Low
Confidence
86% confidence
Finding
The feature bullet '中文优化: 符合中国客服风格' directs the skill toward a specific language and locale style. Because no user choice or opt-in is provided nearby, this can violate language/locale policy for general-purpose skills.

Natural-Language Policy Violations

Low
Confidence
84% confidence
Finding
The notes restrict the skill to Chinese ecommerce platforms and Chinese script generation, which amounts to a fixed locale/language assumption. The file does not indicate that users can choose another language or confirm this locale-specific behavior.

Static analysis

No suspicious patterns detected.