ClawHub
Back to skill

Security audit

style-learner

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed writing-style analysis helper, with one scoping issue around broad activation triggers but no evidence of hidden, destructive, or unrelated behavior.

Before installing, be aware that this skill may activate on general writing-style requests and may store representative excerpts in generated profiles. Use it with exemplar text you are comfortable analyzing and retaining in a style guide.

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

High
Confidence
97% confidence
Finding
The trigger list includes generic terms like "style," "voice," "tone," and "learning," which overlap heavily with normal conversation and many unrelated writing tasks. The file does not provide narrowing context, explicit activation constraints, or negative examples to distinguish when this skill should activate versus when it should not.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.