Security audit
Ai Product Canvas
Security checks across malware telemetry and agentic risk
Overview
This skill is a planning template for AI product decisions and does not request unusual access, persistence, or execution authority.
Before installing, expect this skill to help draft AI product planning artifacts and to ask for product, user-problem, data, and ownership details. Avoid entering confidential or regulated data unless your normal workspace and model-use policies allow it, but the artifact itself shows no unusual security behavior.
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
64/64 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.