Back to skill

Security audit

openclaw-eho

Security checks for vulnerabilities and agentic risk

Overview

This plugin is a straightforward Korea apartment transaction lookup tool that sends user-provided query fields to its disclosed real-estate API.

Install this only if you want OpenClaw to query a third-party Korean real-estate service with the region, apartment name, transaction type, and date range you provide. Expect Korean-focused behavior and limited supported regions; no evidence shows local file access, credential use, or persistent system changes beyond normal plugin installation.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The file begins with Korean-only descriptive text and does not state that the skill is intentionally limited to Korean speakers or provide an opt-in language choice. That can conflict with language/locale policy expectations when users are not given a documented choice of language.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The invocation guidance is overly broad and encourages users to issue natural-language requests like 'just ask' or 'Please use the installed plugin eho' without defining clear activation boundaries, expected parameters, or when the plugin should or should not be used. In an agent environment, this can cause unintended plugin invocation, parameter confusion, or misuse of the skill in contexts the user did not clearly authorize.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The tool description and several user-visible strings are written only in Korean, which imposes a specific language on users without any opt-in or alternative locale. The policy for this category requires flagging language or locale constraints when the skill does not offer a language choice or document a justified regional limitation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The document describes the skill as tied to Korean real-estate data and only supports major regions in South Korea, but it does not explicitly frame this as a region-specific tool limitation or offer any user choice around locale. Because locale restrictions are a natural-language policy concern, this should be documented more clearly to avoid implying a default locale constraint without opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.