Security audit

File Organizer

Security checks for vulnerabilities and agentic risk

Overview

This file-organizing skill is mostly coherent, but it can move many local files automatically without a preview or confirmation.

Install only if you are comfortable with a skill that can reorganize files in folders such as Desktop, Downloads, or Documents. Use it only on directories you have backed up or do not mind rearranging, and prefer asking for statistics/view mode first where possible.

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 (7)

Missing User Warnings

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The skill performs destructive filesystem changes immediately after parsing a user message, moving files in the target directory without an explicit confirmation or dry-run step. In an agent context, ambiguous prompts, accidental activation, or prompt injection through surrounding conversation could cause unintended bulk reorganization and disrupt user workflows or software that expects files to remain in place.
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 '识别并清理重复文件' without warning that duplicate cleanup can delete or move user data incorrectly, especially when content-based matching is imperfect. In a file-management context, destructive operations are inherently risky because a mistaken cleanup can cause irreversible data loss.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger phrases are very broad, common words like '整理' and '分类' that can match many ordinary conversations unrelated to filesystem operations. This can cause accidental skill activation in the wrong context, increasing the chance of unintended file actions if the runtime grants the skill filesystem capabilities.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The description, activation keywords, and user-facing prompts are all hard-coded in Chinese, and activation depends on Chinese terms like 整理 and 分类. This creates a language-policy issue because the skill forces a specific language experience without explicit user opt-in or a documented justification for being Chinese-only.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The description labels the skill as a Chinese version and the keywords are exclusively Chinese, indicating a language-specific constraint in the skill metadata. The file does not mention any user choice, opt-in, or justification for restricting the skill to Chinese, which can violate language/locale policy requirements.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 87% confidence
Finding: The description and tags explicitly present the skill as a Chinese version, but the document does not state that language is selectable or optional. This can violate language/locale policy when a skill constrains interaction to a single language without offering user choice or documenting a justified regional limitation.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.