Back to skill

Security audit

Proxmint proxy setup

Security checks for vulnerabilities and agentic risk

Overview

This proxy-setup skill needs review because its default examples expose proxy passwords to network observers without warning.

Before using password authentication, ask the provider for a supported encrypted connection. Where suitable, use the documented option to authorize a fixed server IP without sending a password. Destination HTTPS alone does not protect the proxy login. Both bundled files were reviewed; live service behavior and the optional external container were not tested.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
references/clients.md
Finding

Proxy credentials are transmitted over an unencrypted connection

Content
View full analysis

Impact

A network observer can recover the proxy credentials and use the user's proxy account and bandwidth. HTTPS to the destination does not protect the preceding proxy authentication exchange.

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

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 57)May include surrounding context.

md
3. Write the configuration from the matching snippet in `references/clients.md`. Keep the user's existing HTTP

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 52)May include surrounding context.

md
## Workflow

1. Read credentials from the environment variables `PROXMINT_USERNAME` and `PROXMINT_PASSWORD`.
   - Never ask the user to paste their password into the chat, and never write it into code, config files or
     examples.
   - If the user shares a password anyway, don't repeat it. Suggest keeping it in their environment or a secrets
     manager.