OpenClaw Seedance Prompt Library
Security checks across malware telemetry and agentic risk
Overview
This is a bounded prompt-writing skill with an optional public GitHub search helper and no evidence of hidden access, persistence, credential use, or destructive behavior.
Safe for normal prompt-writing use. Before installing, note that the optional helper contacts GitHub to retrieve live public prompt examples, and review generated or adapted prompts for attribution, licensing, and IP concerns before publishing derived work.
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
VirusTotal
62/62 vendors flagged this skill as clean.