Security audit
Expert Product Feedback
Security checks across malware telemetry and agentic risk
Overview
The reviewed artifacts are coherent with developer and operations skill workflows, and no scanner or artifact evidence shows hidden or harmful behavior.
Before installing, confirm you want these skills to access the relevant developer workspace and any configured Axiom, Sentry, Grafana, Slack, Convex, or model-provider accounts. Use least-privilege tokens and review local memory/config behavior for operational skills.
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
63/63 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.