ClawHub
Back to skill

Security audit

Social Science Journal Abstract Polisher

Security checks for vulnerabilities and agentic risk

Overview

This is a prompt-only academic abstract editing skill with no code execution, persistence, credential access, or hidden behavior.

Safe to install for polishing English social science abstracts. Users should expect it to rewrite abstract text and append a short revision note; it is not designed for full manuscript editing or non-English abstracts unless modified.

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
91% confidence
Finding

The manifest description says to use the skill when 'polishing, revising, or improving an abstract,' which is a broad natural-language trigger without explicit constraints or negative examples. Although the domain is social science abstracts, the activation guidance does not clearly distinguish when this skill should or should not be selected among general writing-editing skills.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The instruction states that the user provides 'one English-language abstract,' which encodes a language constraint in natural-language policy terms. The file does not offer a language choice, opt-in, or a clear region/compliance justification for restricting operation to English.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.