build-brand-design-faq-page
Security checks across malware telemetry and agentic risk
Overview
This is a simple instruction-only skill for drafting brand-design FAQ content, with no evidence of hidden code, credential access, persistence, or unsafe actions.
Review generated FAQ copy before publishing, verify factual claims from web_search, and avoid entering confidential brand strategy, customer data, or unreleased product details unless you are comfortable using those inputs with the agent and its configured search/chat providers.
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.