ClawHub
Back to skill

Security audit

show sysinfo

Security checks for vulnerabilities and agentic risk

Overview

This system-report skill is mostly coherent, but it defaults to collecting sensitive host, network, login-session, and local-account details without a clear opt-in boundary.

Review before installing. Use it only in environments where the requester is allowed to see host networking, active sessions, and local account names. Prefer adding an explicit confirmation step or removing `cat /etc/passwd` and detailed session/network output from the default report.

A.I.G

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
Findings (1)

other

Warning
Location
SKILL.md:26
Finding

Excessive Collection of Host, Network, and Local Account Information

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Credential Access

High
Category
Privilege Escalation
Confidence
98% confidence
Finding

Including cat /etc/passwd instructs the skill to retrieve account enumeration data that is not necessary for basic system health checks. Even if modern systems store password hashes elsewhere, /etc/passwd still reveals valid usernames, service accounts, shells, home directories, and system structure, which materially assists attacker reconnaissance.

Content

Scanner excerpt · SKILL.md (reported line 29)May include surrounding context.

md
| 网络接口 | `ip addr` 或 `ifconfig` |
| 登录用户 | `who` |
| 系统运行时间 | `uptime` |
| 用户信息 | cat /etc/passwd |

## 执行步骤

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill’s trigger description is broad enough to match common requests about system status and host details, which increases the chance of accidental activation. In this context, unintended execution can expose sensitive operational data such as hostnames, network configuration, logged-in users, and software/environment details without the user explicitly consenting to that level of collection.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill collects and displays sensitive system and account information, including network interfaces, logged-in users, and /etc/passwd, but the documentation does not clearly warn users about the scope or sensitivity of that disclosure. This creates a real risk of oversharing reconnaissance data that could aid lateral movement, targeting, or privilege escalation in a compromised or shared environment.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

L39 规定“以 Markdown 报告形式输出”，且全文内容默认使用中文表述，没有说明是否遵循用户当前语言偏好或允许选择输出语言。按本规则，若技能在自然语言层面强制特定语言/locale 且未提供 opt-in 或选择，属于政策风险。

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.