prompt-polisher
Security checks across malware telemetry and agentic risk
Overview
This is a simple prompt-rewriting skill with no executable code, network access, credential use, or persistence.
This skill is reasonable to install if you want help polishing prompts. It rewrites text you provide, so avoid including passwords, API keys, private documents, or other sensitive information in prompts unless you are comfortable having that text processed by your agent.
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.
