ClawHub
Back to skill

Security audit

小红书配图生成器

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small, purpose-aligned Xiaohongshu cover-image generator that writes one local JPEG and shows no evidence of hidden access, network use, persistence, or unsafe execution.

Before installing, be aware that generated output is saved to a fixed local file path, /root/.openclaw/workspace/xhs_cover.jpg, so rerunning the script can replace the previous image. The skill otherwise stays within its stated image-generation purpose.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Natural-Language Policy Violations

Medium
Confidence
93% confidence
Finding
The user-facing description and usage guidance are entirely in Chinese, which can impose a language-specific experience without any opt-in or explanation. Under the policy, language constraints should either be optional for the user or clearly justified as region-specific.

Missing User Warnings

Low
Confidence
88% confidence
Finding
This markdown file documents that the skill saves an image as `xhs_cover.jpg`, which affects user data on the local filesystem. The description states the output location/name but does not include any explicit user warning or caution about overwriting or creating a local file.

Natural-Language Policy Violations

Low
Confidence
94% confidence
Finding
The module docstring is written as a fixed Chinese-only description, indicating a language-specific skill behavior without any visible user opt-in or documented locale justification. This matches the policy category for language or locale constraints that are imposed without offering a choice.

Static analysis

No suspicious patterns detected.