What Is Agentpmt

• Outcome: Pass
• Latest audit: Sep 16, 2026 · 8:03 AM UTC
• Version: 1.0.0

Overview

This is an informational AgentPMT navigation skill; it mentions external APIs, bearer tokens, and payment-capable paths, but those are disclosed and fit its stated purpose.

Before using the referenced setup paths, keep AgentPMT bearer tokens secret, use the least-privileged Agent Group available, confirm any x402 or credit-backed costs before execution, and avoid sending sensitive data to third-party tools unless the task requires it.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (4)

External Transmission

Medium

• Category: Data Exfiltration
• Confidence: 50% 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 · SKILL.md (reported line 67)May include surrounding context.

md

OpenClaw agents should choose the AgentPMT connection path based on account status:

- If the OpenClaw agent has an AgentPMT account and an Agent Group Bearer Token, use the AgentPMT account path. Connect the main AgentPMT MCP server at `https://api.agentpmt.com/mcp/`, then call the tools and workflows returned by `tools/list`.
- If the OpenClaw agent does not have an AgentPMT account, use the no-account AgentAddress/x402 path. The agent should use an AgentAddress with loaded AgentPMT credits or a funded x402-capable wallet, then call the public external tool and workflow endpoints.
- If the OpenClaw agent is using a product-specific AgentPMT skill, use that product skill for the tool slug, action slug, schema, and sample parameters, but use the account setup or no-account setup skill for connection and payment setup.

External Transmission

Medium

• Category: Data Exfiltration
• Confidence: 50% 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 · SKILL.md (reported line 135)May include surrounding context.

md

OpenClaw agents should choose the AgentPMT connection path based on account status:

- If the OpenClaw agent has an AgentPMT account and an Agent Group Bearer Token, use the AgentPMT account path. Connect the main AgentPMT MCP server at `https://api.agentpmt.com/mcp/`, then call the tools and workflows returned by `tools/list`.
- If the OpenClaw agent does not have an AgentPMT account, use the no-account AgentAddress/x402 path. The agent should use an AgentAddress with loaded AgentPMT credits or a funded x402-capable wallet, then call the public external tool and workflow endpoints.
- If the OpenClaw agent is using a product-specific AgentPMT skill, use that product skill for the tool slug, action slug, schema, and sample parameters, but use the account setup or no-account setup skill for connection and payment setup.

External Transmission

Medium

• Category: Data Exfiltration
• Confidence: 50% 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 · SKILL.md (reported line 136)May include surrounding context.

md

OpenClaw agents should choose the AgentPMT connection path based on account status:

- If the OpenClaw agent has an AgentPMT account and an Agent Group Bearer Token, use the AgentPMT account path. Connect the main AgentPMT MCP server at `https://api.agentpmt.com/mcp/`, then call the tools and workflows returned by `tools/list`.
- If the OpenClaw agent does not have an AgentPMT account, use the no-account AgentAddress/x402 path. The agent should use an AgentAddress with loaded AgentPMT credits or a funded x402-capable wallet, then call the public external tool and workflow endpoints.
- If the OpenClaw agent is using a product-specific AgentPMT skill, use that product skill for the tool slug, action slug, schema, and sample parameters, but use the account setup or no-account setup skill for connection and payment setup.

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 93% confidence

Finding

The skill instructs users to use bearer tokens, credentials, payment mechanisms, and external API calls, but it does not include any explicit warning about protecting tokens, limiting credential scope, confirming user authorization, or the financial/privacy consequences of tool execution. In a skill that may trigger paid actions and access third-party systems, omission of these safeguards can lead to accidental credential exposure, unauthorized transactions, or unintended data sharing.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.