CinePrompt

Security checks across malware telemetry and agentic risk

Overview

This is a text-only skill for creating AI video prompts and storyboards, with only a minor risk of activating too broadly.

Safe to install for AI video prompt and storyboard drafting. Be aware it may activate on broad prompt-writing or storyboard terms; narrowing the trigger phrases would reduce accidental use.

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
89% confidence
Finding
The trigger list includes very broad generic terms such as '提示词', '分镜', and '视频脚本', which can activate the skill for many ordinary requests beyond its intended scope. Over-broad routing can cause unintended invocation, making the agent apply this skill in the wrong context and increasing the chance of prompt hijacking, irrelevant behavior, or bypass of more appropriate safeguards.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal