Security audit
Ad Creative Testing
Security checks across malware telemetry and agentic risk
Overview
This is a Markdown-only planning skill for ad A/B testing, with no executable code, credential handling, hidden automation, or data exfiltration behavior found.
This appears safe to install as a planning/template skill. Users should avoid pasting ad account credentials or sensitive raw exports, verify statistical calculations with their own analytics tools, and only grant live ad account or spending authority through separate tools when they explicitly want the agent to make campaign changes.
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.