ClawHub
Back to skill

Security audit

MathProofs-Claw

Security checks for vulnerabilities and agentic risk

Overview

This skill transparently connects an agent to a MathProofs-Claw service to search, submit, and prove Lean theorems, with expected API-key use and no hidden persistence or local system access found.

Install this only if you trust mathproofs.adeveloper.com.br with your MathProofs API key and with theorem statements or Lean proofs you submit. Treat submitted theorem/proof content as data sent to a third-party service, and avoid placing private material in usernames, theorem names, statements, or proof text.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The declared purpose says the skill interacts with the Lean-Claw Arena, but the content actually instructs the agent to register accounts, obtain API keys, and communicate with a different backend domain, mathproofs.adeveloper.com.br. This mismatch can mislead users and policy systems about what the skill really does, increasing the chance of unauthorized account provisioning, secret transmission, and trust decisions based on inaccurate metadata.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding

The skill requires both environment access and outbound network use but does not declare any explicit tool scope such as allowed tools or permissions. That weakens least-privilege controls and makes it easier for an agent to access secrets like MATHPROOFS_API_KEY and transmit them to a remote service without clear platform-enforced constraints.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The registration tool sends user-supplied data to an external service and the handler itself provides no built-in confirmation, disclosure, or minimization before transmission. In an agent-tool context, this is risky because an LLM may invoke the tool automatically and disclose a chosen username or other future schema fields to a third party without meaningful user awareness.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
85% confidence
Finding

This tool performs an outbound POST to a third-party domain with user-controlled content. External transmission is expected for this skill, but it still creates a real privacy and data-exfiltration boundary because anything placed in args is sent off-platform and could be triggered by the agent without sufficient user scrutiny.

Content

Scanner excerpt · index.ts (reported line 44)May include surrounding context.

ts
required: []
      },
      handler: async (args: any) => {
        const response = await fetch("https://mathproofs.adeveloper.com.br/api/auth/agent-register", {
          method: "POST",
          headers: { "Content-Type": "application/json; charset=utf-8" },
          body: JSON.stringify(args)

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · index.ts (reported line 69)May include surrounding context.

ts
return { error: "Missing 'MATHPROOFS_API_KEY' environment variable. Please configure it in your OpenClaw agent settings." };
        }

        const response = await fetch("https://mathproofs.adeveloper.com.br/api/theorems", {
          method: "POST",
          headers: {
            "Content-Type": "application/json; charset=utf-8",

Static analysis

No suspicious patterns detected.