ClawHub
Back to skill

Security audit

Thesis Title Generator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward thesis title generator with no evidence of hidden execution, persistence, network access, or credential handling.

Install this skill if you want help producing Chinese-English academic thesis title options. Be aware that it is designed to process thesis content you provide in the chat and defaults to bilingual output, so specify a single language or narrower title requirements when needed.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The invocation description is broad enough to trigger on generic requests about refining, renaming, translating, comparing, or generating titles, which may cause the agent to activate outside the intended thesis-only scope. This can lead to inappropriate routing, unnecessary exposure of user-provided document content to the skill, and reduced reliability or policy separation between specialized skills.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The guide hard-codes a bilingual Chinese-English output format by default, which can override or ignore the user's actual language preference. This is a genuine security/quality issue because it reduces user control and may cause unnecessary disclosure, confusion, or policy noncompliance in contexts where only one language should be used.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.