Security audit
code-memory-skill
Security checks across malware telemetry and agentic risk
Overview
This documentation-only skill is coherent for local code indexing, with its main privacy and supply-chain risks disclosed.
Before installing, treat this as a local code-indexing tool: only index repositories you are comfortable storing in a local SQLite database, ensure secrets are ignored before indexing, keep SSE bound to 127.0.0.1, and vet or pin external package/model artifacts for sensitive environments.
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
65/65 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.