Back to skill

Security audit

Sysinfo Demo

Security checks for vulnerabilities and agentic risk

Overview

This skill only reports basic local system information with read-only commands, and its behavior is disclosed and proportional to its purpose.

Install this only if you are comfortable with the agent revealing local system details such as disk usage, kernel/OS information, uptime, and load when asked about machine status. It does not request write access or elevated privileges.

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
  • 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 (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill metadata and instructions are written to produce output in Chinese, but there is no indication that the user can choose another language or that the locale restriction is intentional and justified. This can violate language/locale policy when users have not opted into Chinese responses.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger text is broad enough to match common conversational requests like asking how the machine is doing, which can cause the skill to activate unexpectedly. Because the skill executes host commands (df, uname, uptime) and reveals local system information, overbroad invocation increases the chance of unintended disclosure of environment details.

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 31)May include surrounding context.

md
- 总是先把原始命令打出来,再附一句简短总结,不要花哨格式化;
- 不要编造数字——命令失败就老实说;
- 拒绝任何需要 sudo 或会写入文件系统的请求。

Static analysis

No suspicious patterns detected.