Back to skill

Security audit

Thesis Writer

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese thesis-writing helper with no executable code, credential use, persistence, or hidden data handling.

Before installing, users should understand this skill is tailored to Chinese academic thesis conventions and may be unsuitable for theses written under other language or citation-style expectations without adapting the rules.

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

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The writing constraints require specific Chinese academic phrasing such as using '本文'/'本章' and Chinese/English full-name formatting on first mention. This imposes a language/locale-specific policy on all use without stating that it is optional or limited to Chinese thesis contexts.

Content

No source excerpt is available for this finding.