Security audit
ia-refine-prompt
Security checks across malware telemetry and agentic risk
Overview
This is a prompt-refinement skill made of markdown instructions, with only a disclosed optional save step after user confirmation.
Safe to install for prompt refinement. Only approve the optional save action if you want the refined prompt stored in your workspace, and avoid putting secrets or private data into prompts you ask it to refine.
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.