Security audit
Tvs Architect
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only architecture and debugging guidance skill with no executable code, install hooks, persistence, or hidden behavior.
Install this skill if you want an agent to give architecture or debugging advice based on repository evidence. Expect it to read relevant code, configuration, tests, and logs you provide or allow access to, and avoid exposing unrelated secrets in those materials.
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.
Static analysis
No suspicious patterns detected.