ClawHub
Back to skill

Security audit

article-to-science-video

Security checks across malware telemetry and agentic risk

Overview

This is a text-only workflow for turning user-provided articles into science-video scripts, with no executable code or hidden persistence found.

Install if you want help planning science-video scripts from articles, papers, or reports. Provide only the link, pasted text, or local file you intend the agent to read, and confirm first if the request is merely summarization or translation rather than video-script creation.

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
87% confidence
Finding
The trigger description uses an open-ended phrase ('等需求时触发'), which can cause the skill to activate for loosely related requests beyond the author's intended scope. In an agent environment, overly broad invocation can route unrelated user content into this workflow, increasing the chance of inappropriate execution, unexpected file/link access, or confusion with other skills.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.