Back to skill

Security audit

蒲公英异地组网

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent guide for managing Oray/PgyVPN SD-WAN networks, with real operational risk that users should handle carefully.

Install only if you intend to let an AI client manage your PgyVPN/Oray SD-WAN resources. Treat the MCP API key like a password, keep it out of chats, screenshots, repositories, and shared dotfiles, and review every network, device, password, or delete operation before confirming it, especially on production or remote-access networks.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (8)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The README instructs users to copy a configuration JSON containing an MCP secret key into local config files without warning that the key is sensitive. This creates a realistic risk of credential exposure through screenshots, repo commits, shared dotfiles, backups, or overly broad filesystem access by other tools.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The README advertises destructive and state-changing capabilities such as updating/deleting networks and binding/unbinding devices, but does not warn that these actions can disrupt connectivity, orphan devices, or impact production remote access. In the context of an AI-operated network-management skill, omission of operational-risk warnings increases the chance of unsafe use and accidental outages.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger list includes broad terms such as '组网', '远程办公', '内网穿透', and device/member keywords that can match many generic networking or remote-access requests, causing the skill to activate outside the user's intended scope. In this skill's context, unintended invocation is more dangerous because the skill guides users toward configuring MCP access and managing real SD-WAN resources, which can expose credentials or prompt network-changing actions.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill tells users to generate an MCP API key and paste it into local configuration files, but it does not clearly label the key as a sensitive secret, warn against sharing/checking it into source control, or recommend least-privilege storage practices. Because this key enables AI-driven management of SD-WAN networks and devices, leakage could allow unauthorized network enumeration, member management, password resets, or destructive changes through the MCP server.

Content

No source excerpt is available for this finding.

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
70% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · SKILL.md (reported line 169)May include surrounding context.

bash
# Debian/Ubuntu
sudo dpkg -i pgyvisitor_xxx_amd64.deb
sudo apt-get install -f

# CentOS/RHEL

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
70% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · SKILL.md (reported line 170)May include surrounding context.

bash
# Debian/Ubuntu
sudo dpkg -i pgyvisitor_xxx_amd64.deb
sudo apt-get install -f

# CentOS/RHEL

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
70% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · SKILL.md (reported line 173)May include surrounding context.

bash
# Debian/Ubuntu
sudo dpkg -i pgyvisitor_xxx_amd64.deb
sudo apt-get install -f

# CentOS/RHEL

Vague Triggers

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

该 README 描述了技能用途和覆盖范围,但没有提供明确的触发短语、限定条件或不应触发的负例。对于适用于 manifest/markdown 的触发质量要求而言,这种仅描述能力、不定义调用边界的写法容易造成激活条件模糊。

Content

No source excerpt is available for this finding.