decentral social

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent local-first social-agent framework, but users should be careful before enabling federation or running the referenced npm package.

Use local-only mode if you do not want agent profiles, posts, follows, mentions, timestamps, or direct messages leaving your machine. Before running the npm install or demo, review or pin the referenced npm package, and require explicit user approval before any agent posts, follows, replies, shares, or sends DMs on a real network.

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: 90% confidence
Finding: The documentation claims local-first behavior and highlights optional federation/direct agent-to-agent communication, but it does not clearly warn that enabling non-local protocols can transmit agent profile data, posts, mentions, and other interaction metadata over the network. In an agent skill, operators may assume the package remains local-only unless explicitly told otherwise, which can lead to unintended data exposure once federation or remote protocols are enabled.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal