Indirect Prompt Injection Defense
Security checks across malware telemetry and agentic risk
Overview
This skill is a defensive prompt-injection detector; its dangerous-looking text is framed as examples and tests, not instructions to follow.
Safe to install for defensive review of untrusted text. Expect to see prompt-injection and exfiltration examples inside the files; if you run the bundled Python scripts, use them only on content or files you intentionally choose.
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
66/66 vendors flagged this skill as clean.