Security audit

Wanxiang Scroll Interactive

Security checks for vulnerabilities and agentic risk

Overview

The skill is a storytelling/game helper, but it needs review because it claims special instruction priority and asks users to install an unpinned companion package.

Review the skill before installing, especially if you rely on strict output formats or instruction boundaries. Treat # commands as skill-local only, pin or verify the companion package before use, and avoid entering sensitive personal details unless you are comfortable with them being converted into story state or novel text.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Insecure DependenciesIntroduces malicious components through unsafe dependency sources
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 (2)

T01 · Skill Instruction Hijacking

Error

Location: references/02-core-protocols.md:22
Finding: Agent Instruction Hierarchy and Persona Hijacking
Content: View full analysis
Remediation: View remediation

T08 · Insecure Dependencies

Warning

Location: SKILL.md:30
Finding: Unpinned and Unverified Companion Skill Installation
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (12)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The entire skill interface, commands, examples, and instructions are presented only in Chinese, including required invocation syntax such as #文风 and #行动. There is no indication that users may choose another language or that the skill is intentionally limited to a Chinese-only region or compliance context.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: This markdown file defines the skill entirely in Chinese and specifies output structures, commands, and behavior in Chinese, with no indication that the user can choose another language or opt in to this locale. Under the policy, forcing a specific language without user choice is a natural-language policy violation unless the locale constraint is clearly documented and justified.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The trigger phrases include very generic prompts such as “/深入浅出” and “/知识写作”, which can easily overlap with ordinary user writing requests outside the intended scope of this chapter. That makes the skill prone to accidental activation or over-application, causing the agent to steer responses into this framework when the user did not explicitly ask for it.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 86% confidence
Finding: The entire skill file is written as mandatory game-design instructions in Chinese, with no indication that users may choose another language or that the skill is intended only for a Chinese-language context. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The entire skill file is written in Chinese and presents all user-facing invocation and behavior descriptions only in that language, with no indication that the user can choose another language. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is explicitly documented and justified.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: This markdown file presents all instructions, commands, and usage guidance only in Chinese, and there is no indication that users can opt into another language or that the skill is intentionally restricted to a Chinese-speaking audience. That can violate a language/locale policy requiring user choice or explicit justification for locale constraints.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 95% confidence
Finding: This markdown file presents all instructions and content in Chinese, and there is no natural-language indication that users may choose another language or that the skill is intentionally restricted to a Chinese-speaking context. Under the policy rule for language or locale, forcing a specific language without user opt-in is a policy concern.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: The section instructs the model to directly use a specific second-person style (“直接说‘你’”) and discourages alternatives without asking for user preference. This is a policy-shaping behavior that can override user-desired tone or context, reducing user control and potentially producing inappropriate style in formal, academic, or enterprise settings.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 93% confidence
Finding: This markdown file presents all instructions and user-facing examples entirely in Chinese, and does not mention any option to use another language. Under the policy for natural-language violations, forcing a specific language without user opt-in can be a locale/language policy issue.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 78% confidence
Finding: The entire skill content is written in Chinese and does not indicate that users may choose another language or locale. Under the stated policy, fixed language behavior without user opt-in can be a natural-language policy violation unless the locale restriction is explicitly justified.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The skill explicitly describes 'silent' background generation of novelized content after each turn without any notice, consent, or retention/transparency language. Even if framed as a gameplay feature, silent capture and transformation of user inputs into persistent content can create privacy, expectation, and data-governance issues, especially if sensitive roleplay or personal details are entered.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The file presents the skill title, descriptions, and all core commands entirely in Chinese, including invocation phrases such as 新游戏, 开始, and 继续. Because the documentation does not mention any user-selectable language option or justify a locale restriction, this appears to impose a specific language/locale by default.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.