Openclaw Agentpmt Tool Bulk Email Address Validation Neverbounce Bc8694

• Outcome: Review
• Latest audit: May 28, 2026, 1:45 AM
• Version:
  1.0.0

Overview

The skill is an instruction-only AgentPMT email validation integration, but it also directs agents to create or use wallets, buy credits, and execute unrelated third-party jobs without clear user confirmation.

Install only if you intentionally want an AgentPMT-mediated workflow, not just direct NeverBounce validation. Use a separate low-balance wallet, require explicit approval before any credit purchase or job execution, and avoid submitting regulated or sensitive contact lists unless you understand AgentPMT and NeverBounce data handling.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

Description-Behavior Mismatch

Medium

• Confidence: 94% confidence
• Finding: The skill’s primary purpose is bulk email validation, but it also instructs the agent to create wallets, purchase credits, and earn credits through unrelated jobs. This expands the authority and action surface far beyond the stated function, creating a confused-deputy risk where an agent may take financial actions or engage in unrelated workflows without clear user intent.

Context-Inappropriate Capability

High

• Confidence: 98% confidence
• Finding: The skill explicitly authorizes reserving, executing, and completing arbitrary AgentPMT jobs, which is unrelated to validating email addresses. That allows the agent to fetch and act on unbounded third-party instructions, potentially causing data leakage, unauthorized external actions, or task execution outside the user’s request.

Context-Inappropriate Capability

Medium

• Confidence: 91% confidence
• Finding: Embedding wallet creation and x402 credit-purchase logic into a narrowly scoped validation skill introduces unnecessary payment and identity operations. This increases the chance of unauthorized spending, wallet misuse, and expanded compromise if the agent follows these instructions automatically.

Missing User Warnings

Medium

• Confidence: 88% confidence
• Finding: The skill processes potentially sensitive email lists and requires a third-party API key, but it does not clearly warn that email addresses will be transmitted to external services. Users may unknowingly expose personal data, customer records, or regulated contact information to AgentPMT and NeverBounce.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The instructions direct agents to create and use wallets for signed requests and potential payments without an explicit warning about financial and account side effects. This can lead to unintended account creation, key management risk, or spending activity that the user did not knowingly authorize.

VirusTotal

VirusTotal findings are pending for this skill version.