Back to skill

Security audit

基于六维人生模型的通用电脑文件自动整理技能,支持语义分类、集合格文件夹、按需创建目录等规则

Security checks for vulnerabilities and agentic risk

Overview

This file-organization skill is not malicious, but it should be reviewed because it can reorganize many local files without a required preview or confirmation.

Use this only on a narrow folder you choose, ideally after a backup. Before allowing changes, ask the agent to produce a dry-run manifest with every planned move or rename, confirm there are no overwrites or symlink escapes, and avoid running it across your home folder, system folders, synced drives, or active project directories.

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

Warning
Location
skill.md:29
Finding

Unconfirmed Bulk Filesystem Mutation Based on Filename-Only Classification

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The description is written as a Chinese-only skill description and the operational instructions later require Chinese naming conventions and folder labels, but the document does not offer a user language/locale choice. This can violate language policy when a skill imposes a specific language without opt-in or clear region-specific justification.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill explicitly authorizes local filesystem modifications (move, rename, create) but provides no user-facing safety gate, dry-run mode, scope restriction, or warning about the consequences. In a file-management skill, semantic misclassification or path mistakes can silently reorganize large amounts of user data, causing effective data loss, workflow disruption, or difficult recovery even without deletion.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill mandates a particular naming scheme tied to Chinese labels and explicitly discusses Chinese naming choices, but does not allow the user to choose another language or locale. This is a natural-language policy concern because the locale constraint is imposed rather than offered as an option.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The instruction to complete all organization in one pass and avoid repeated confirmation increases the risk of unsafe bulk filesystem changes without user review. In this context, the skill is designed to make many semantic judgments automatically, so removing checkpoints materially raises the chance of widespread unintended file movement and user lockout from expected locations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.