Security audit

去 AI 味内容引擎

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only writing helper for making platform posts sound less AI-like, with no hidden execution, data access, persistence, or posting authority.

Install this if you want a Chinese-oriented content rewriting workflow for 小红书, X, or 知乎. Review outputs before use, especially factual claims and platform tone, because the skill asks for concrete details and source labels but does not independently verify or publish content.

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 (6)

Natural-Language Policy Violations

Medium

Confidence: 83% confidence
Finding: The README presents the skill entirely in Chinese and frames its purpose around Chinese-language platform content generation, but does not state that language choice is optional or user-directed. This can amount to a locale/language policy issue if the skill defaults to a specific language without opt-in.

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The trigger phrases are very broad and mirror common natural user requests such as '重写成更像人写的' or '口语化', which can cause the skill to activate in many ordinary rewriting contexts without clear user intent to invoke this specific behavior. In an agent system, over-broad activation can lead to unintended content transformation, policy bypass of safer default flows, or unexpected handling of user text across platforms.

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The skill advertises multiple broad, natural-language trigger phrases such as “口语化”, “太像 AI 了”, and “重写成更像人写的”, which are common user expressions and can cause accidental or overly broad invocation. In an agent ecosystem, this increases the chance the skill activates in contexts where users did not intend platform-specific rewriting, potentially leading to unintended content transformation or policy bypass attempts framed as stylistic editing.

Natural-Language Policy Violations

Medium

Confidence: 93% confidence
Finding: This markdown file contains natural-language guidance that effectively forces a specific language/locale style, including Chinese first-person and opinionated phrasing examples. Under the policy, language or locale constraints should either be optional or clearly justified; this file presents them as mandatory style rules without opt-in.

Natural-Language Policy Violations

Medium

Confidence: 88% confidence
Finding: This markdown file contains platform templates that prescribe Chinese-language content for 小红书/知乎 sections and English-language content for the X section, but it does not state that language should match user preference or platform/audience choice. That creates a natural-language locale policy concern because the skill implicitly forces output language by template rather than offering an opt-in or documented justification.

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: The checklist instruction is written as a mandatory Chinese-language directive ('发布建议前，逐项打勾') and the entire file is localized to Chinese with no indication that users may choose another language. This can violate language/locale policy when a skill implicitly forces a specific language without opt-in or justification.

Static analysis

No suspicious patterns detected.