Back to skill

Security audit

Filesystem

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward filesystem command reference with disclosed file search, copy, move, delete, and analysis examples.

Install this only if you want a Chinese-language filesystem command reference. Be careful with the delete, move, rename, and in-place replacement examples, especially batch commands, and ask the agent to preview affected files before running any mutation.

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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill description is broadly scoped to many common filesystem tasks, which can cause over-invocation and expose users to powerful file-manipulation guidance in contexts where a narrower skill would suffice. Because the skill includes destructive operations like move/delete, broad matching increases the chance that routine requests trigger potentially risky instructions unnecessarily.

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 339)May include surrounding context.

md
- 考虑使用 `rm -i` 交互式删除

⚠️ **权限注意**:
- 某些操作可能需要 sudo
- 系统目录操作要谨慎
- 考虑文件权限问题

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

The file presents the operational documentation in Chinese, while the manifest header includes English text, and there is no statement that the skill is Chinese-only or that users may choose their preferred language. This can violate language/locale policy when a skill implicitly forces one language without opt-in or justification.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.