Back to skill

Security audit

Novel Writer Agent

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward novel-writing guidance skill with no executable code, network access, credential handling, or hidden high-impact behavior.

Before installing, confirm that the skill's Chinese-first novel workflow and any material-library behavior match how you want your writing workspace managed. There is no inspected evidence of code execution, credential use, network access, or deceptive behavior.

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 (1)

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The manifest description is written entirely in Chinese and frames the skill as a Chinese novel-writing agent, while only briefly mentioning bilingual output. Under the policy rule, language constraints should either offer explicit user choice or clearly justify the locale; this file does not explicitly state that language selection is optional or user-driven.

Content

No source excerpt is available for this finding.