ClawHub
Back to skill

Security audit

Long To Cards

Security checks across malware telemetry and agentic risk

Overview

This skill coherently turns user-provided long-form content into social card packages and disclosed image-production handoffs, without hidden execution, credential use, or persistence.

Install this if you want an agent to transform supplied articles, notes, transcripts, or outlines into card packages and usually continue into image generation. Use delivery_mode=copy_only when you only want copy or prompts, and review claim verification, hot tags, and captions before publishing anywhere.

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
86% confidence
Finding
The skill description is broadly scoped ('transform long-form content' across multiple platforms and outputs) without clear invocation boundaries or trigger constraints. In agent environments, overly broad descriptions can cause the skill to be selected in unintended contexts, which may lead to inappropriate processing of sensitive user content or unexpected downstream actions such as automatic handoff to image-production workflows.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.