ClawHub
Back to skill

Security audit

OnlyFans API Access

Security checks for vulnerabilities and agentic risk

Overview

The skill’s core OnlyFansAPI analytics behavior is coherent, but it is broad enough to warrant review because it can access sensitive multi-account business and earnings data with limited scoping guidance.

Install only if you intend your agent to query OnlyFansAPI.com with your API key and view connected account analytics. Use it for explicit analytics/reporting requests, avoid broad or casual OnlyFans prompts when the key is available, and treat returned earnings, model, link, and account data as sensitive business information.

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
  • 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
Findings (2)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The README explicitly enables access to sensitive OnlyFans business and account analytics across multiple connected models and instructs users to configure an API key, but it provides no warning about privacy-sensitive data exposure, least-privilege handling, retention, or transmission to a third-party service. In an agent-skill context, this omission is meaningful because an autonomous agent may fetch, aggregate, and surface highly sensitive financial and creator-performance data without clear user consent or safeguards.

Vague Triggers

Medium
Confidence
96% confidence
Finding
The trigger phrase 'Use when users ask about anything related to OnlyFans' is excessively broad and can cause the skill to activate for many unrelated or weakly related requests. Because this skill has network access and is designed to query sensitive account analytics, unintended invocation could expose private business data or cause unnecessary external API calls in contexts where the user did not explicitly request this integration.

Static analysis

No suspicious patterns detected.