Security audit
content-material-scorer
Security checks across malware telemetry and agentic risk
Overview
This skill is a transparent Markdown-based workflow for scoring short-form content ideas and does not request unusual access or hidden execution.
Installers should expect this skill to help evaluate and record content ideas. Review any private or third-party product details before pasting them into an AI thread or cloud table; the skill itself explicitly warns not to upload private or unpublished third-party data without confirmation.
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
65/65 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.