LFIT

Security checks across malware telemetry and agentic risk

Overview

LFIT is a coherent local image-generation skill with disclosed optional external sharing features that users should understand before enabling.

Install only if you are comfortable trusting the external @lowwattlabs/lfit npm package and any server/model downloads it performs. Keep the server bound to 127.0.0.1, avoid lfit-quick if you do not want prompts sent to a public cloud service, and leave Telegram credentials unset or use --no-telegram unless you want generated images sent to Telegram.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
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

Findings (1)

Missing User Warnings

Medium

Confidence: 96% confidence
Finding: The README strongly emphasizes privacy and that no data leaves the machine, but later notes that generated images can be automatically pushed to Telegram if credentials are set. While marked optional, this is a network transmission of user-generated content and the description does not explicitly warn about the privacy impact or contrast it with the earlier local/private positioning.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal