Review Skill Improver
Security checks across malware telemetry and agentic risk
Overview
This skill is a markdown-only review aid that analyzes feedback logs and suggests evidence-based improvements without hidden execution, persistence, or credential use.
This skill appears safe to install for analyzing review feedback logs. Users should still review any generated recommendations before applying them to real review skills, especially if future automation is added to create PRs or modify skill files.
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.