ClawHub
Back to skill

Security audit

OnlyFans运营加速器

Security checks for vulnerabilities and agentic risk

Overview

This skill is a markdown-only Chinese guide for subscription-platform creator operations, with no code execution, persistence, credential access, or hidden data handling.

Install this only if you want Chinese-language operational guidance for subscription-platform creator businesses. Review platform rules, age/legal requirements, tax obligations, and any third-party automation tools yourself before acting on its business or messaging templates.

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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list is very broad and includes generic business and creator terms such as '内容付费', '创作者运营', '粉丝管理', and 'subscriber growth', which can cause the skill to activate in contexts far beyond the intended OnlyFans/subscription-platform workflow. Overbroad activation increases the chance of unintended routing, irrelevant advice, and accidental invocation in adjacent topics, which is especially risky for a monetization skill touching adult-platform-adjacent subject matter.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

Mandating Chinese-only output without a user language choice can create accessibility and usability failures when users interact in another language or expect locale-appropriate compliance and platform terminology. While not a direct exploit primitive, it can lead to misunderstood guidance, user confusion, and unsafe operational decisions if important constraints are not clearly understood.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

This markdown file presents all operational guidance, templates, and instructions exclusively in Chinese. Under the policy, forcing a specific language without user opt-in or a documented regional justification is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.