Back to skill

Security audit

ensp

Security checks for vulnerabilities and agentic risk

Overview

This skill is a focused eNSP topology-file generator with no evidence of hidden execution, data theft, persistence, or privilege abuse.

Installers should expect the skill to create local `.topo` files for eNSP. Review generated topologies before opening them in eNSP, especially if using Cloud devices or adapter settings, but the reviewed artifact does not show hidden or unrelated behavior.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (3)

Hidden Instructions

High
Category
Prompt Injection
Confidence
70% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · references/topo-reference.md (reported line 9)May include surrounding context.

md
<?xml version="1.0" encoding="UNICODE" ?>
<topo version="1.3.00.100">
    <devices>
        <!-- Device definitions -->
    </devices>
    <lines>
        <!-- Connection lines -->

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The manifest says to "Always use" the skill when the user asks to "create, generate, or design a network topology diagram," which is a broad class of requests that can include many non-eNSP contexts. Although Huawei/eNSP examples are mentioned, the trigger logic does not clearly distinguish when generic topology-diagram requests should not invoke this skill.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
76% confidence
Finding

Line L538 states charset | 1=UTF-8/ASCII, 134=GBK/Chinese, which introduces a language/locale-specific encoding option in the skill reference. Because the document presents this locale-specific setting without offering user choice guidance or explaining a region-specific requirement, it may conflict with language/locale neutrality policy.

Content

No source excerpt is available for this finding.