ClawHub
Back to skill

Security audit

Academic Writing Refiner

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only academic writing refinement skill with no code execution, persistence, credential handling, or hidden data movement.

Install this skill if you want academic-paper editing assistance. Be aware it may activate for broad academic or LaTeX writing requests, so users should clarify when they want only light grammar edits or non-academic writing help.

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
Category
Not specified by scanner
Confidence
96% confidence
Finding

The manifest description says to use the skill whenever a user asks to "improve, polish, refine, edit, or proofread" academic or research writing, and also when they ask for writing help with pasted LaTeX. These trigger phrases are broad and lack explicit exclusion conditions or negative examples, which increases the chance of matching routine editing requests beyond the intended narrow activation context.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger criteria are broad enough to match many generic writing-editing requests, especially anything involving polishing, proofreading, or pasted LaTeX. This can cause the skill to activate outside its intended academic-CS scope, leading to over-collection of user content, misrouting, or inappropriate style transformations, though it does not directly enable code execution or privilege escalation.

Content

No source excerpt is available for this finding.