Back to skill

Security audit

内置插件使用说明/手册

Security checks for vulnerabilities and agentic risk

Overview

This skill is a benign OpenClaw plugin catalog helper that reads local plugin metadata and documentation without installing, enabling, deleting, or exfiltrating anything.

Install this only if you want a Chinese-language helper for inspecting OpenClaw built-in plugin information. It may reveal local OpenClaw plugin inventory, statuses, capabilities, and documentation excerpts to the agent, but the inspected artifacts do not show mutation, persistence, credential harvesting, or external upload 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (6)

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · references/builtin-plugins.md (reported line 226)May include surrounding context.

md
LINE 渠道插件,用于接入 LINE Bot 消息。

- 作用:处理 LINE 私聊、群组或会话消息。
- 常见操作:配置 Channel Access Token、Secret、Webhook 和群策略。
- 说明:适合东亚地区常用的 LINE 场景。

## llm-task

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding

The skill invokes shell commands and reads local reference files, but it does not declare any explicit tool scope such as allowed-tools or permissions. That creates an authorization gap where an agent may execute shell/file operations more broadly than reviewers or runtime policy expect, increasing the chance of unintended command execution or filesystem access.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest description and the entire SKILL.md content are written in Chinese, with no indication that the skill can respond in other languages or that Chinese is a justified locale requirement. This creates a natural-language locale constraint without user opt-in, which matches the language/locale policy violation criteria.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The documentation describes a high-privilege phone-control capability that can enable camera, screen recording, and write-like actions, but the warning is limited and does not clearly spell out privacy, consent, and system-impact risks. In a plugin guide, this can normalize dangerous capability enablement without sufficient guardrails, increasing the chance of misuse or accidental over-privileging by operators.

Content

No source excerpt is available for this finding.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/openclaw_plugin_catalog.py (reported line 92)May include surrounding context.

python
cli,
            *args,
        ]
    proc = subprocess.run(
        command,
        check=False,
        capture_output=True,

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

The entire skill document is presented only in Chinese and does not indicate that language choice is optional or that the content is intentionally restricted to a Chinese-speaking audience. Under the policy, forcing a specific language without user opt-in can be a natural-language locale violation.

Content

No source excerpt is available for this finding.