Prompt Injection Tester
Security checks across malware telemetry and agentic risk
Overview
This is an instruction-only skill for authorized LLM prompt-injection testing; the risky-looking phrases are disclosed test examples, not hidden commands.
Install this only for systems you own or have permission to test. Prefer staging or isolated test environments, get explicit approval before running resource-heavy or data-mutating tests, and remove any test prompts or poisoned documents added during RAG or tool-call testing.
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.