Security audit
Knowledge Evidence Finder
Security checks across malware telemetry and agentic risk
Overview
This skill is a small text-extraction helper with no executable code, persistence, credential access, or hidden side effects in the artifacts reviewed.
This appears safe to install for simple marker extraction from text you provide. As with any skill, avoid giving it unrelated sensitive documents unless that content is necessary for the task.
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
63/63 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.