Security audit
AI生成
Security checks across malware telemetry and agentic risk
Overview
This skill matches its stated purpose of managing AI ad-creative generation tasks and shows no hidden file, credential, shell, network, or persistence behavior.
This appears reasonable to install for ad creative generation workflows. Treat prompts and generation parameters as visible task data, avoid entering secrets or confidential campaign details, and add count limits or per-user scoping if using it in a shared or high-volume environment.
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
66/66 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.