ClawHub
Back to skill

Security audit

Thesis Revision Editor

Security checks for vulnerabilities and agentic risk

Overview

This skill edits academic thesis documents and saves revised copies, with no evidence of hidden execution, exfiltration, persistence, or privilege abuse.

Install this if you want an agent to revise and save academic drafts. Review the destination path before using it on sensitive thesis files, and ask for preview-only output if you do not want a revised file created.

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

Vague Triggers

Medium
Confidence
92% confidence
Finding
The skill description is extremely broad and overlaps with common writing and editing requests, which can cause the agent to invoke this skill in many situations beyond narrow thesis-revision use. Overbroad routing increases the chance of unintended file access or file-writing behavior being triggered for ordinary editing tasks, especially because the skill also instructs saving revised outputs.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill repeatedly instructs the agent to save revised files, including creating files in the current working directory or next to a supplied local file, without requiring an explicit user confirmation immediately before the write. This can lead to unintended filesystem modification, surprise artifact creation, or writes to sensitive directories if the user provides a path that the agent can access.

Static analysis

No suspicious patterns detected.