Security audit
Review Diagnostics
Security checks across malware telemetry and agentic risk
Overview
This is a manuscript review helper with disclosed local checklist and validation scripts, and I found no evidence of hidden data access or unsafe behavior.
Before installing, understand that the helper scripts can create docs/reviews/<article-name>/checklist.json and validate local review.md/source files when you run them. This is expected for the workflow, but run it only in projects where that local review directory convention is acceptable.
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
59/59 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.
