Prompt Debugger
Security checks across malware telemetry and agentic risk
Overview
This is a prompt-debugging instruction skill with no code, installation scripts, credentials, persistence, or external access.
Safe for normal prompt debugging use. Review any rewritten prompts before using them as production system or agent instructions, and avoid pasting secrets or confidential data into prompts unless you are comfortable exposing that information to the active AI session.
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.