Seedance 2.0 Prompt Writing

Security checks across malware telemetry and agentic risk

Overview

This skill appears to be a prompt-writing helper for Seedance/Jimeng video generation, with no evidence of code execution, data access, persistence, or exfiltration.

Install this if you want Seedance/Jimeng video prompt assistance. Be aware it may activate on broad video-prompting requests, so use it intentionally for Seedance-related work and review generated prompts before submitting them to any video platform.

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
90% confidence
Finding
The skill description is broadly scoped to 'writing high-quality prompts' for many multimodal video-generation scenarios, without clear trigger boundaries limiting when the skill should activate. In an agent system, this can cause over-triggering on generic prompt-writing or video-help requests, leading the skill to take over unrelated user tasks and increasing the chance of unsafe or policy-misaligned guidance being surfaced in the wrong context.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal