Security audit
xlsx-skill
Security checks across malware telemetry and agentic risk
Overview
The skills are mostly coherent developer-maintenance helpers, but one review helper defaults to launching a nested agent with full local access and can pass diffs to fallback review tools.
Review the autoreview skill before installing. It is not evidence of malware, but users should only run it in repositories they are comfortable exposing to local reviewer tools, prefer the no-yolo/sandboxed mode for routine review, and be aware that moderation and Convex workflows can make real account, deployment, or data changes when invoked.
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.