Security audit

Content Adaptation for Xiaohongshu, Douyin, Bilibili, WeChat

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Chinese social-media copywriting helper and does not show hidden data access, persistence, posting, or destructive behavior.

Install this if you want Chinese-platform content adaptation. Review outputs before publishing, and be aware that it drafts copy and image prompts but does not itself post content or handle account credentials.

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 description lists trigger phrases as "多平台分发、发到XX平台", and especially "发到XX平台" is a highly generic phrase that could appear in ordinary conversation rather than uniquely signaling this skill. The file does not provide narrowing context, exclusions, or negative examples to prevent accidental invocation.

Natural-Language Policy Violations

Medium

Confidence: 90% confidence
Finding: The entire skill specification is written as a Chinese-only operating instruction for the agent, with no indication that the user may choose another language or that the locale restriction is required for a region-specific compliance reason. This matches the policy category for language/locale constraints imposed without opt-in.

Natural-Language Policy Violations

Medium

Confidence: 93% confidence
Finding: The entire skill specification requires operation and output in Chinese, including Chinese platform names, field descriptions, and style guidance, but it does not mention any opt-in, fallback, or user-selectable language behavior. Under the policy for natural-language violations, forcing a specific language without user choice is a reportable locale-policy issue.

Natural-Language Policy Violations

Medium

Confidence: 94% confidence
Finding: 该文件整体以中文定义用户与 Agent 的交互范式、确认文案和生成内容，呈现出默认且唯一使用中文的行为。根据规则，若技能强制特定语言而未提供用户选择或明确的地区性正当说明，属于自然语言策略违规。

Natural-Language Policy Violations

Medium

Confidence: 93% confidence
Finding: The package description is entirely in Chinese and presents the skill as generating platform-specific copy for Chinese social platforms, with no indication that users can choose another language or locale. This creates a natural-language locale constraint that is not documented as optional or justified as a region-specific requirement.

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: The document is entirely written in Chinese and includes audience-specific phrasing such as '姐妹们' and Chinese-platform-specific templates, with no indication that language choice is optional. This can violate language/locale policy when a skill or reference forces a specific language without user opt-in or documented regional justification.

Natural-Language Policy Violations

Medium

Confidence: 96% confidence
Finding: The file description and all user-facing output strings are in Chinese, including headings and field labels. Because this is a general formatting script with no documented region-specific justification or user opt-in for locale, it creates a language-policy issue by forcing one language.

Natural-Language Policy Violations

Low

Confidence: 89% confidence
Finding: This markdown file contains natural-language guidance exclusively in Chinese for prompts, platform descriptions, and output examples. Under the policy, forcing a specific language without user opt-in can be a locale/language policy violation unless the constraint is explicitly documented and justified.

Static analysis

No suspicious patterns detected.