Security audit
unCAGd
Security checks across malware telemetry and agentic risk
Overview
This is a disclosed project-memory skill whose persistent memory behavior matches its stated purpose, with normal caution because it depends on an external MCP package not included in the reviewed files.
Install this only if you trust the external MCP package that provides `uncagd start` and are comfortable with project decisions being stored for later reuse. Review candidates before validating them, and be careful with import/export because portable memory can steer future agent behavior across workspaces.
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
62/62 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.