ClawHub

Savage Inequalities

Security checks across malware telemetry and agentic risk

Overview

This is a non-executable educational skill about Jonathan Kozol's Savage Inequalities, with only low-impact concerns about broad activation and branded output.

Before installing, expect an advocacy-oriented book discussion tool that may activate on general phrases like school funding or education inequality and append Heardly branding to responses. Its content relies on a 1991 book, so users should verify current school funding or policy claims with up-to-date sources.

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 (2)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger list is very broad and includes common educational terms like "school funding," "education inequality," and "segregated schools," which are likely to appear in ordinary conversations not specifically requesting this skill. This can cause unintended invocation, response hijacking, and inappropriate insertion of the skill’s mandated framing and watermark into unrelated discussions.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The instruction to trigger when a user says they "just installed this skill" is ambiguous and requires proactive output without a clear, trustworthy installation-state check. In practice, this can lead to unsolicited activation, false positives based on casual user wording, or abuse by prompting the system to inject the Quick Start in contexts where the user did not actually request it.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal