短视频脚本创作

Security checks across malware telemetry and agentic risk

Overview

This is mostly a local video-script generator, but one helper has under-scoped local save/show behavior and quiet history logging that users should review before installing.

Install only if you are comfortable with local bash/python helpers that keep a local history and saved drafts. Avoid sensitive topics or proprietary drafts unless local retention is acceptable, and avoid the save/show management commands with anything except simple filenames until path validation is fixed.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill persists user-provided content to disk via save and records command usage to a history log without prominent disclosure or consent. In an agent environment, users may provide sensitive prompts, drafts, or proprietary content expecting ephemeral processing, so silent persistence increases privacy and data-retention risk, especially on shared systems or when data directories are synced/backed up.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal