智能代码审查助手
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only code review skill with no executable code or hidden sensitive behavior in the reviewed package.
This skill appears safe as reviewed, but it is mostly documentation and does not include the actual Node review tool it references. Before running node scripts/review.mjs, confirm the script comes from a trusted intended source and is not an unrelated file already present in your project.
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.