Security audit
AI 绘画提示词库 Pro
Security checks across malware telemetry and agentic risk
Overview
No supplied scanner signal or available artifact evidence shows harmful behavior, but the actual target skill content was not present for full local review.
The available signals support allowing this skill, but confidence is limited because the target artifact content was not available for direct inspection. Before installing, review the skill's SKILL.md and any bundled files for commands it asks the agent to run, credential requirements, write actions, network calls, or background persistence.
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
63/63 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.