Back to skill

Security audit

净盘师 DiskKeeper

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed local disk-cleanup tool, but its deletion safeguards rely on environment-derived Windows paths, which makes it worth reviewing before use.

Install only if you are comfortable with a local cleanup tool that can delete files after explicit confirmation. Run doctor, plan, and clean without --yes first, inspect the listed paths carefully, avoid elevated/admin shells, and do not use it from wrapped or modified environments where USERPROFILE, LOCALAPPDATA, APPDATA, SystemRoot, TEMP, or TMP may be altered.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Error
Location
scripts/disk_butler.py:86
Finding

Environment-Controlled Cleanup Roots Permit Deletion Outside Trusted Cache and Temporary Directories

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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
95% confidence
Finding

The file’s user-facing description and command output are written exclusively in Chinese, and there is no indication that users can opt into another language or locale. Under the policy rule, forcing a specific language without user choice is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The entire skill description is presented only in Chinese, including usage, safety notes, and warnings, with no indication that other languages are supported or that the skill is intentionally limited to a Chinese-speaking audience. Under the policy rule for language or locale constraints, this can be a natural-language policy issue because users are not given an opt-in or alternative.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest sets locale: zh-CN and states the skill is designed for Chinese users, which imposes a language/locale constraint. The file does not offer a selectable language option or explicit user opt-in within the skill, so this is a natural-language locale policy concern under the stated rule.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The docstring for cmd_report says it turns '释放多少 / 零误删 / 动了什么' into a shareable report, implying disclosure of what was acted on. The function actually prints aggregate statistics and a share card, but nowhere lists the specific files/directories touched, so the documentation overstates what the command reports.

Content

No source excerpt is available for this finding.