Evidence URL Verifier
Security checks across malware telemetry and agentic risk
Overview
This is a narrow instruction-only skill for checking evidence links and named artifact paths, with no hidden code or persistence.
Use this skill when you want an agent to verify evidence links and local artifact references. Avoid checking private tokenized URLs, internal network addresses, or sensitive local paths unless that limited reachability or existence disclosure is acceptable.
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
64/64 vendors flagged this skill as clean.