Security audit
gstack Investigate
Security checks across malware telemetry and agentic risk
Overview
This is an instruction-only debugging skill whose behavior fits its stated purpose, with a privacy note because it asks agents to save debug reports to memory.
Install this if you want a structured debugging workflow. Before using it on private or production code, configure your agent to redact secrets, customer data, private paths, and sensitive logs before external search or saved memory reports, or disable memory writes if your runtime allows it.
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.