ClawHub
Back to skill

Security audit

03 Acquisition Retention

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent Chinese-language community group-buying marketing playbook with manual analysis snippets, but users should apply privacy and anti-spam controls before using its outreach templates.

Installers should treat this as a manual marketing operations guide. Before using its customer segmentation, private-message, QR-code, or referral templates, confirm that the contact list was collected lawfully, users consented where required, unsubscribe/opt-out paths are present, outreach limits are enforced, and KPI formulas are reviewed before business decisions.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill provides targeted re-engagement and behavioral segmentation playbooks that assume operators can message users based on purchase history and inactivity, but it omits any consent, lawful-basis, opt-out, or data-minimization guidance. In practice this can drive unauthorized profiling and direct marketing to users, creating privacy/compliance risk and increasing the chance of abusive outreach at scale.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

L0504-L0515 的 docstring 将输入描述为“第1周活跃用户数”和后续各周留存用户数，但 Returns 却标注为“次日/7日/30日留存率”。实际计算在 L0516-L0518 明确使用 week2/week3/week4 相对 week1 的比值，语义上是周留存而非次日留存，属于文档对代码行为的主动误导。

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The acquisition scripts encourage QR-code onboarding, private outreach, group invites, and incentive-driven sharing without warning about what user data is collected, how contacts were obtained, or how consent is captured. That makes it easy to operationalize opaque data collection and unsolicited marketing, especially in community/group contexts where social pressure can mask improper consent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The manifest description is entirely in Chinese and the rest of the skill consistently assumes Chinese-language operation without offering a language choice or documenting a justified locale restriction. This can violate language/locale policy when a skill effectively forces one language without user opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.