Security audit

File Organizer Zh 1.0.0

Security checks for vulnerabilities and agentic risk

Overview

This Chinese file-organizer skill does what it says, but it can immediately move many local files based on broad trigger words without a preview, confirmation, or undo path.

Install only if you are comfortable with a skill that can reorganize files in Desktop, Downloads, Documents, or a supplied Windows path as soon as it is invoked. Use it first on a small test folder, and avoid broad requests unless the agent confirms the exact target and planned moves before execution.

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

SkillSpector

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (8)

Missing User Warnings

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The skill performs destructive file-system changes immediately after inferring a target directory from a natural-language message, without an explicit confirmation step or dry-run preview. In an agent setting, ambiguous phrasing, prompt injection through surrounding context, or simple user misunderstanding could cause large-scale unintended file moves in Desktop, Downloads, or an arbitrary parsed path, disrupting workflows and effectively causing denial of access to expected file locations.
Content: No source excerpt is available for this finding.

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 70% confidence
Finding: Without declared permissions the skill's intent is opaque and cannot be validated.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill advertises automatic classification and duplicate cleanup but does not warn users that these actions may move, overwrite, or delete files. In this context, the missing warning materially increases the risk of destructive operations being performed without informed consent, leading to data loss or difficult-to-reverse reorganization.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger keywords are very broad terms like '整理' and '分类', which are common in normal conversation and can cause the skill to activate unintentionally. In a file-management skill, accidental invocation is dangerous because it could reorganize files or initiate duplicate cleanup without the user explicitly intending that action.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The description, activation keywords, and user-facing messages are all Chinese-only, and activation depends on Chinese trigger words such as '整理' and '分类'. This enforces a specific language/locale behavior without user opt-in or an explicit documented regional constraint.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The package name, description, and keywords explicitly mark the skill as Chinese-only (e.g. 'zh', '中文版', '中文'), but the manifest does not state that users can choose another language or that the locale restriction is required for a region-specific purpose. This creates a natural-language policy concern because it appears to force a specific language without opt-in.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 86% confidence
Finding: The description and tags explicitly label the skill as a Chinese version, but the file does not indicate that users may choose another language or that the locale restriction is required for a justified region-specific purpose. This can conflict with language-choice policy when a skill implicitly enforces one language by default.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The manifest slug file-organizer-zh indicates a Chinese-language or locale-specific variant, but this file provides no natural-language justification or evidence of user opt-in for that locale constraint. Under the policy, forcing a specific language without documented choice can be a locale policy violation.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.