Back to skill

Security audit

Xiaohongshu Viral Notes Generator V2

Security checks for vulnerabilities and agentic risk

Overview

This is a small Markdown-only skill for generating Xiaohongshu-style Chinese social posts, with no bundled code, dependencies, credential access, persistence, or hidden execution behavior.

Install only if you want a Chinese Xiaohongshu-focused writing helper. Treat its exposure and engagement claims as marketing, and review any export destination before saving generated content.

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 Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
83% confidence
Finding

The natural-language description and usage are centered on generating Xiaohongshu notes in Chinese, and the file does not indicate any user opt-in or configurable language selection. A skill that forces a specific language or locale without choice can violate language/locale policy requirements.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest declares version "2.0.0" at L004, but the documentation header states "v1.0.0" at L013. This is an active contradiction in the file's own documentation about what version the skill is.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

This markdown file describes a file-writing capability via the --export option, including an example command and parameter entry, but provides no user warning about overwriting files, choosing safe paths, or the fact that content will be written to disk. For markdown files, behaviors that affect user data or system state should be disclosed clearly.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The section title "v1.0.0 功能" conflicts with the manifest version "2.0.0" declared at L004. This creates intent/documentation divergence by describing the skill as version 1.0.0 while the manifest presents it as 2.0.0.

Content

No source excerpt is available for this finding.