Security audit

Banshee's Last Cry Game CN

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language horror text-adventure skill with disclosed game-state saving and no evidence of code execution, credential access, exfiltration, or privileged persistence.

Install this only if you want a Chinese-language horror mystery experience and are comfortable with violent and psychological thriller content. Expect it to keep local fictional progress in game_state.json; host routing should keep its generic helper phrases within active game sessions.

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
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 (19)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill is entirely written in Chinese and does not provide any language selection, fallback, or notice for users who do not understand Chinese. This creates a real safety and usability risk because users may not understand game instructions, content warnings, or state-management directions, which can lead to misuse, confusion, or accidental exposure to unwanted horror/violent content.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The file’s metadata, instructions, prompts, and example outputs are entirely in Chinese, and the skill directs the AI to operate in that mode throughout the game flow. There is no user opt-in, alternative locale handling, or statement that the skill is intentionally limited to Chinese-speaking users for a justified regional purpose.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The skill content is entirely written to operate in Chinese and explicitly structures gameplay output without any mechanism to detect, ask for, or honor the user's language preference. This can exclude or confuse users, cause consent and usability issues, and in multilingual environments may lead to unsafe misunderstandings of important instructions or narrative choices.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The skill content is entirely authored in Chinese and its execution instructions implicitly require Chinese-only gameplay without offering a language-selection path or documenting a justified locale restriction. This can exclude users, override user language preferences, and create unsafe UX assumptions in multilingual deployments, though it does not appear to be an actively malicious instruction.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 86% confidence
Finding: The file is entirely written as mandatory Chinese-language gameplay instructions and does not indicate that the user may choose another language. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is clearly documented and justified.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The file’s name, description, and all interaction instructions are written exclusively in Chinese, and the skill directs the model to begin outputting the scene immediately in that language. There is no indication that the user can opt into another language or that the locale restriction is explicitly justified as a region-specific requirement.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The file’s name and description, along with the full body of operational instructions, are written exclusively in Chinese and direct the interaction in that language. There is no indication that the user can choose another language or that the locale restriction is required for a region-specific purpose, which conflicts with the language/locale policy criteria.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill content is entirely in Chinese and the instructions constrain output behavior without offering any user language choice or documenting a required locale. This can reduce accessibility, cause user confusion, and make the skill less reliable in multilingual environments, though it is not a direct security exploit in this narrative-game context.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The file’s title and description, along with the full instruction set, are entirely in Chinese and present the interaction format as fixed rather than optional. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly justified, which is not present here.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The skill’s name and description, together with the full instruction set, are written as fixed Chinese-language content and provide no indication that users may opt into another language. Under the policy, forcing a specific language without user choice is a natural-language locale violation unless the regional constraint is explicit and justified.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The file is written to operate only in Chinese and provides no mechanism to honor user language preference or obtain opt-in. This can cause misleading or inaccessible interactions for users who expect another language, and in safety-sensitive or high-stakes contexts it may prevent users from understanding important content or controls.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The file's name and description, along with all operational instructions and content, are written exclusively in Chinese, indicating the skill is designed to run in a fixed language. The policy scope here is natural-language behavior, and the file does not mention any user opt-in, language selection, or region-specific justification for this constraint.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill content is entirely written to operate in Chinese and explicitly constrains runtime behavior without offering a user-language fallback or selection mechanism. This can exclude or mislead users who interact in other languages, causing accessibility and usability issues, but it does not by itself create a direct security compromise such as code execution or data exfiltration.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The file presents the skill name, description, instructions, prompts, and interaction text entirely in Chinese, with no indication that users may choose another language. This creates a language/locale constraint that is not documented as optional or justified as region-specific.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The skill’s name, description, usage examples, and response templates are all written to operate in Chinese, with no indication that users may choose another language. Because the file does not document this as a region-specific or opt-in constraint, it appears to impose a language choice by default.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill advertises very broad trigger phrases such as '谁还活着？' and '谁最可疑？' without any explicit routing constraints tying them to the game context. In a host assistant, these common phrases can cause accidental or inappropriate activation, leading the skill to intercept unrelated user requests and expose or manipulate in-game state unexpectedly.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The skill name, description, usage examples, and all user-facing output are written entirely in Chinese, with no indication that the user can choose another language. Under the policy, forcing a specific language without opt-in is a natural-language policy violation unless the locale restriction is clearly documented and justified.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: This markdown skill file presents all instructions, prompts, and interaction text exclusively in Chinese, 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 concern.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 87% confidence
Finding: The skill name, description, triggers, instructions, and example outputs are all presented exclusively in Chinese, and the file does not indicate that language selection is optional. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy concern unless the locale restriction is clearly documented and justified.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.