ClawHub
Back to skill

Security audit

Social Science Journal Abstract Polisher

Security checks across malware telemetry and agentic risk

Overview

This is a prompt-only academic abstract editing skill with no code, install actions, persistence, credential use, or external access.

Safe to install for academic abstract editing. Users should apply it only to abstracts they intend to revise and review the output for scholarly accuracy, because editing prompts can still change nuance even when they are instructed not to invent content.

SkillSpector

By NVIDIA
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 (1)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The skill description is broad enough to match many ordinary editing requests, which can cause unintended invocation outside the narrow academic-abstract use case. Overbroad triggering is dangerous in agent systems because it can route unrelated user content into a transformation pipeline that changes wording, tone, or structure without the user intending to use this specialized skill.

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.