Security audit

dir-organizer

Security checks for vulnerabilities and agentic risk

Overview

This folder-organizing skill is not malicious, but it under-declares the filesystem and subprocess access needed to move files, so users should review it before installing.

Install only if you are comfortable with a local script that can move files inside a chosen directory. Use preview or --json first, back up important folders before --apply, and be aware the package metadata currently understates the filesystem and subprocess access the skill actually needs.

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

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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

Findings (8)

Scope Creep

High

Category: Not specified by scanner
Confidence: 99% confidence
Finding: The manifest explicitly declares filesystem: false while the skill's documented purpose is to inspect directories and, with --apply, move files into subfolders. This is a dangerous permission mismatch because policy engines or reviewers may treat the skill as non-file-touching even though its documented behavior requires reading and writing the filesystem, enabling unapproved file modification or data loss.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: This file contains natural-language instructions that effectively force a specific language/locale for users and maintainers. Under the policy, that is a violation unless the skill offers language opt-in or clearly documents a justified regional constraint, which this file does not.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The trigger guidance includes broad everyday phrases such as '整理一下这个文件夹' and '把文件按类型分好', which can activate the skill in ordinary conversation without strong user intent verification. Because this skill can ultimately move files when run in apply mode, overly broad activation increases the risk of accidental invocation in a sensitive directory.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 79% confidence
Finding: The output schema promises JSON on stdout, but the usage text describes human-readable preview reports and command-style execution without a clearly defined machine-readable contract. This inconsistency can cause automation or wrappers to mis-parse results, potentially leading to incorrect trust decisions or unintended follow-on actions after file operations.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The file hard-codes Chinese folder names for categories and also uses Chinese in CLI descriptions and output. This imposes a specific language/locale on all users without opt-in, which matches the policy category for language or locale violations.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 85% confidence
Finding: The document is explicitly bilingual in Chinese and English, but it does not state whether the skill can interact in other languages or defer to the user's preferred locale. Under the stated policy, forcing a specific language or locale without opt-in can be a natural-language policy issue.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 80% confidence
Finding: The primary description and display naming are Chinese-first, and the file does not state that language should follow the user's preference. Under the policy, language or locale should not be forced unless the user is given a choice or the constraint is justified.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The file’s user-facing description is entirely in Chinese and does not offer an alternative language or state that the skill is intentionally limited to Chinese-speaking users. This can violate a language/locale policy when users are not given a choice or opt-in.
Content: No source excerpt is available for this finding.