Security audit

Xhs Post Factory

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Chinese Xiaohongshu post-writing helper that reads user-provided content and creates local draft output files, with no evidence of hidden execution, credential access, network retrieval, posting, or persistence.

Install this if you want Chinese Xiaohongshu-style draft posts generated from documents. Before using it in a sensitive or synced folder, note that it writes xhs-post.md and xhs-post.json next to the input file; review those drafts before publishing because the skill does not post to Xiaohongshu itself.

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

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: The file states `默认语言: 中文为主，夹少量英文术语`, which imposes a language choice by default. Under the policy, forcing a specific language without offering user choice or documenting a justified locale constraint is a natural-language policy violation.

Natural-Language Policy Violations

Medium

Confidence: 94% confidence
Finding: The template states that the skill is used to convert papers into Xiaohongshu 'paper interpretation' posts in Chinese, which imposes a specific language/locale on the output. Because the file does not offer user opt-in or alternative language handling, this is a natural-language locale policy concern under the stated rules.

Missing User Warnings

Low

Confidence: 93% confidence
Finding: The skill explicitly writes `xhs-post.md` and `xhs-post.json` into the input file's directory, but the description does not warn users about this side effect. That can lead to unexpected file creation in sensitive or shared directories, especially when the source directory is under version control, synced storage, or contains stricter write expectations.

Natural-Language Policy Violations

Low

Confidence: 82% confidence
Finding: Line L15 instructs that terminology should receive a brief Chinese explanation, which imposes a specific language requirement in the guidance. The file does not indicate that this is optional, user-selected, or limited to a clearly documented region-specific context.

Static analysis

No suspicious patterns detected.