Security audit
Knowledge Evidence Finder
Security checks across malware telemetry and agentic risk
Overview
This is a narrow text-only skill that extracts a document marker from provided text and does not ask for file, network, credential, command, or persistent access.
This appears safe to install for extracting known markers from text you provide. As with any third-party skill from a low-history publisher, use it only for its stated narrow purpose and avoid treating its fixed validation marker as a general knowledge source.
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.
Static analysis
No suspicious patterns detected.