Back to skill

Security audit

个人RPG

Security checks for vulnerabilities and agentic risk

Overview

This is a local Chinese-language personal RPG/task tracker that stores and edits its own JSON files, with no evidence of hidden network, credential, or background behavior.

Install this only if you are comfortable using a Chinese-language CLI that keeps personal task and progress data locally under the OpenClaw workspace. Treat delete and complete commands as data-changing actions, because completed or deleted tasks may no longer remain in the active task list.

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
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (5)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
82% confidence
Finding

The README is written in Chinese and the command examples require Chinese terms such as 角色 and Chinese task/difficulty values, but the document does not state that the skill is region-specific or provide an opt-in language choice. Under SQP-3, forcing a specific language without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

This markdown file describes commands such as complete <ID> and delete <ID> and later shows persistent storage in local JSON files, but it does not warn users that these commands change or remove saved data. For markdown files, SQP-2 applies when behavior affecting user data is described without disclosure about data impact or persistence.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The documented invocation model and examples require fixed Chinese command phrases such as 查看角色, 添加任务, and 完成任务, but the file does not state that this is optional or limited to a Chinese-only context. Under SQP-3, this is a natural-language locale policy issue because the skill appears to enforce a specific language without user opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This code explicitly formats dates using the zh-CN locale and the CLI messaging throughout the file is Chinese-centric, which imposes a specific language/locale on users. The policy allows locale constraints only when documented and justified or when users are given a choice, neither of which is present in this code file.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill documentation explicitly supports deleting tasks and storing persistent user data under a local workspace path, but it does not warn users that their data will be retained locally or that commands may permanently remove entries. This creates a real safety and usability risk because users may unintentionally lose data or expose personal productivity information without informed consent, even though the behavior is not inherently malicious.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.