Security audit
Medium
Security checks across malware telemetry and agentic risk
Overview
This is a writing-assistance skill for improving long-form Medium articles and it does not request code execution, credentials, network access, or persistence.
Reasonable to install for long-form writing help. Users should still independently verify factual claims, citations, legal, compliance, or domain-specific statements before publishing, as the skill itself says it does not replace those checks.
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.
Static analysis
No suspicious patterns detected.