Back to skill

Security audit

Xiaohongshu Booster

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local Xiaohongshu content generator with disclosed, purpose-aligned behavior and no evidence of hidden access, persistence, or exfiltration.

Installers should treat this as a Chinese-market copywriting helper. Review generated claims before posting, especially for skincare, supplements, or medical-adjacent products, and use --output only with a path you are comfortable creating or overwriting.

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
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (12)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
87% confidence
Finding

The skill advertises itself as self-contained but documents an --output option that saves generated content to a file, while the manifest declares no explicit tool scope or permission boundary. In an agent environment, undocumented write capability can lead to unintended file creation or overwrite if the host maps this skill to file-system tools without user-visible constraints.

Content

No source excerpt is available for this finding.

External Model or Provider Selection

Medium
Category
Excessive Agency
Confidence
90% confidence
Finding

Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.

Content

Scanner excerpt · SKILL.md (reported line 8)May include surrounding context.

md
author: ClawHub Community
category: Content Creation
description: Generate 3 viral-ready Xiaohongshu (Little Red Book) notes from a product, scene, or topic — titles, body copy, hashtags, cover-image tips, and publish-time recommendations.
model: agent
tags:
  - xiaohongshu
  - little-red-book

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The file states the skill generates body copy as '150–300 Chinese characters,' which imposes a specific language requirement in the skill behavior. While the skill targets Xiaohongshu, the documentation does not explicitly present Chinese output as a user-selectable option or clearly frame the locale restriction as a documented regional limitation for all uses.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

Line L11 instructs users to use '5-8 Chinese characters max' as a blanket rule. This is a natural-language locale constraint that forces a specific language without user opt-in or any documented justification that the skill is limited to a Chinese-language context.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The title and description define the skill specifically for generating Xiaohongshu notes, and the examples and style enums throughout the schema are entirely Chinese-language oriented. Because the file does not state that this is a region-specific or platform-specific language constraint, it appears to enforce a locale without explicit user opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This JSON schema contains natural-language constraints requiring Chinese output, such as 'recommended under 20 Chinese characters' and '150-300 Chinese characters,' along with Chinese-only examples. That creates a locale/language policy issue because the skill appears to mandate a specific language rather than offering a user choice or documenting a justified region-specific constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The script's natural-language templates, examples, and generated content are all fixed to Chinese and the Xiaohongshu platform context. This enforces a specific language/locale behavior without presenting an opt-in or alternative language choice, which matches the language/locale policy violation criteria.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest describes a skill that generates Xiaohongshu notes with titles, body copy, hashtags, cover-image tips, and publish-time recommendations. The code additionally supports writing output to any user-specified file path, which is a side effect not reflected in the manifest description and is not necessary to the core generation function itself.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file is almost entirely Chinese-language content, including headings and hashtag guidance, and does not indicate that the user can choose another language or that the file is intentionally limited to a Chinese-speaking audience. Under the language/locale policy rule, forcing a specific language without opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
77% confidence
Finding

This reference file presents writing templates partly in Chinese and partly in English, and the punctuation and emoji guidance is framed as a general template set rather than explicitly limited to a Chinese-language or Xiaohongshu-only audience. Because the file does not offer a language choice or clearly justify the locale constraint, it may conflict with a policy requiring user opt-in for language or locale preferences.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

This code writes generated content to a user-specified path, which is a file-modifying operation. Although it prints a success message after writing, there is no confirmation prompt or explicit warning near the argument definition or write path that using --output will create or overwrite a local file.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The file repeatedly specifies Chinese-platform content generation, including the name, description, tags, and keywords centered on Xiaohongshu and Chinese marketing. Under the policy, forcing a specific language or locale without user opt-in can be a natural-language policy violation, and this manifest does not indicate any language choice or opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.