Security audit

互动游戏框架

Security checks for vulnerabilities and agentic risk

Overview

This is a low-impact Chinese-language interactive games skill with no hidden execution, network access, credential handling, or persistent system changes found.

Install this only if you want a Chinese-language interactive game framework. Review the sample trigger before integrating it into an agent so ordinary conversation about games does not accidentally start game mode.

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

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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

Findings (8)

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The README shows the skill being invoked when a message merely includes the broad phrase '玩游戏'. In a general-purpose agent, this can overlap with normal conversation and cause unintended activation, diverting the agent from its primary task or triggering game behavior without explicit user intent. The gaming context makes this somewhat less severe than a destructive skill, but broad activation still increases the risk of accidental execution and prompt-space interference.

Natural-Language Policy Violations

Medium

Confidence: 94% confidence
Finding: The title, description, usage instructions, and all example commands are written only in Chinese, and the documented invocation phrases such as '开始文字冒险游戏' and '开始猜谜游戏' imply Chinese-only operation. This is a natural-language locale restriction without any opt-in, alternative language option, or stated regional justification.

Natural-Language Policy Violations

Medium

Confidence: 91% confidence
Finding: The manifest uses Chinese-only user-facing metadata for the display name and description, which indicates a fixed language/locale without offering user choice or documenting a region-specific reason. Under the policy, forcing a specific language without opt-in is a natural-language policy violation.

Natural-Language Policy Violations

Medium

Confidence: 93% confidence
Finding: The comments, theme labels, prompts, and story text are all Chinese-language only, and there is no natural-language indication that users may choose another language. This can violate a language/locale policy when a skill imposes a specific language without user opt-in or justification.

Natural-Language Policy Violations

Medium

Confidence: 90% confidence
Finding: The file mixes English identifiers with Chinese-only descriptive comments and runtime messages such as game start/save/load notices and error text. Under the stated policy, forcing a specific language without opt-in is a natural-language policy violation unless the locale restriction is explicitly justified, which is not present here.

Natural-Language Policy Violations

Medium

Confidence: 96% confidence
Finding: This JavaScript file contains user-facing strings and documentation exclusively in Chinese, including the game start message and usage instruction. The policy explicitly flags language or locale constraints when a skill forces a specific language without user opt-in, and there is no indication here that users can select another language.

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: The file's natural-language content, including the title, comments, branch text, and all story/dialogue templates, is written exclusively in Chinese. This effectively constrains generated output to a specific language without any user opt-in or documented regional justification, which matches the language/locale policy violation criteria.

Natural-Language Policy Violations

Low

Confidence: 79% confidence
Finding: This markdown file contains user-facing operational instructions exclusively in Chinese, including all headings, steps, and command explanations. Under the policy rule for natural-language violations, forcing a specific language without opt-in can be a locale policy issue when no alternative language choice or justification is provided.

Static analysis

No suspicious patterns detected.