Molt Speak
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only skill for an agent communication protocol, with no executable behavior, credentials, persistence, or hidden local access in the reviewed artifacts.
Treat this as protocol documentation. Before installing or relying on the optional npm SDK, verify the package source, consider pinning a version, and confirm that peer authentication, signature verification, tool-use approval, and PII consent are enforced by the actual implementation.
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
VirusTotal findings are pending for this skill version.