ClawHub
Back to skill

Security audit

Spellcheck

Security checks across malware telemetry and agentic risk

Overview

This is a text-only spellcheck and input-normalization skill with no executable code or hidden installation behavior.

Reasonable to install if you want an agent to quietly interpret obvious typos. For exact wording, benchmarks, code, commands, filenames, or identifiers, quote the text or explicitly ask the agent to preserve it verbatim.

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
94% confidence
Finding
The default prompt says to use the skill to 'safely interpret this request before acting,' which is a broad invocation condition that could overlap with many ordinary requests rather than a narrowly defined spellcheck task. The file does not provide specific trigger phrases, scope limits, or negative examples to clarify when this skill should and should not activate.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.