Back to skill

Security audit

OpenClaw NovelAI Opus Free

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent NovelAI workflow guide that uses account checks and strict cost gates to prevent paid image operations.

Before installing, make sure you are comfortable giving the OpenClaw host access to your NovelAI token and account status. The skill is designed to block paid image operations, but users should still watch the displayed estimates and Usage Limit notes because provider billing behavior can change.

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
  • 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 (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The file includes user-facing example requests such as "小图免费生成" and multiple full example prompts entirely in Chinese, but it does not state that the skill is Chinese-only or offer an alternative language/locale option. That can constitute a language-policy issue because the skill appears to privilege a specific language without explicit user opt-in or justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The documentation lists README.zh-CN.md as the Chinese overview but does not indicate whether users are offered a language choice or whether the skill is intended for a specific locale. Under the policy rule, locale-specific language constraints should be explicitly optional or justified.

Content

No source excerpt is available for this finding.