Security audit

shuangwen-skill

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent Chinese creative-writing skill for generating web-fiction chapters and optional video prompts, with no evidence of hidden code, data access, persistence, or unsafe authority.

Install this if you want a Chinese-language web-fiction generator with optional short-drama prompt output. Be aware that it is not designed as a general multilingual writing assistant, and video generation should be treated as user-directed creative output rather than an automatic action.

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

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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

Findings (6)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The README explicitly labels the skill language as Chinese, and the surrounding description consistently frames the skill as operating only in Chinese without presenting language selection or opt-in. Under the policy, fixed language constraints should either offer user choice or be clearly justified as region-specific; here it appears as a hard requirement for a general creative-writing skill.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The skill description and required reply format are written entirely in Chinese, and the prompt on L018 explicitly requires users to reply in a fixed Chinese format. The file does not offer an opt-in language choice or explain that the skill is intentionally limited to Chinese-only operation, which can violate language/locale policy requirements.
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 instructs the user to reply in a specific Chinese-formatted option pattern, without offering any language choice or documenting a required locale. This can exclude or mislead users who do not read Chinese, and may cause unintended actions or poor consent because the interaction constraints are not transparent.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: This markdown file contains the standalone prompt starter "生成视频。", which is extremely broad and lacks any domain, scope, or constraint. Because it resembles a generic everyday request, it could cause unintended activation or make it unclear when this skill should be used instead of other video-related capabilities.
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 is entirely framed as Chinese output examples, including the title '输出示例' and all example content, with no indication that language selection is optional. This creates a natural-language locale policy concern because it appears to prescribe Chinese-only behavior without user opt-in or a documented region-specific justification.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The markdown template is entirely written in Chinese and instructs generation of a Chinese-style video prompt without any indication that the user may choose another language or locale. This creates a natural-language policy issue because it effectively fixes the interaction language by default rather than offering an explicit language choice.
Content: No source excerpt is available for this finding.