Security audit
Skill Lint
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only skill for reviewing other skills, with disclosed local report output and no executable code or hidden data collection found.
Installers should understand that this skill is meant to read and evaluate skill directories or repositories they choose and may create local review reports for formal assessments. Review archived reports before sharing or committing them, because they can summarize private project structure or findings.
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.