ClawHub
Back to skill

Security audit

Agentpmt Account Mcp Rest Api Setup

Security checks across malware telemetry and agentic risk

Overview

This is a coherent AgentPMT setup guide, but its bearer token should be treated like a password because it can access the Agent Group's tools and workflows.

Install only if you intend to connect an agent or app to AgentPMT. Create a least-privilege Agent Group, add only the tools and credentials needed, protect the Bearer Token like a password, avoid putting real tokens in source control or screenshots, and rotate the token if it may have been exposed.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill instructs users to obtain and use a Bearer Token as the sole credential for MCP and REST access, but it does not warn that this token is sensitive, should not be hardcoded, and must be protected from logs, screenshots, config sync, and source control exposure. In a setup guide whose purpose is authentication and remote tool access, omission of credential-handling guidance materially increases the risk of accidental token leakage and unauthorized use of the attached Agent Group.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The examples show the Bearer Token placed directly in HTTP Authorization headers and environment/config fields, including local client configuration, without warning about exposure through shell history, process inspection, config files, crash reports, or desktop sync/backup tools. Because the token grants access to tools, workflows, and attached credentials for an Agent Group, compromised storage or transmission of that token could enable unauthorized remote actions.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.