a

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Lobster.fun livestreaming helper that can control a public stream, so it is acceptable but should be used with care.

Install this only if you want an agent to operate a Lobster.fun stream. Store credentials in a secret manager or environment variable, rotate them if exposed, require operator approval before going live, and moderate chat-triggered gestures, GIFs, and YouTube videos before they appear publicly.

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 (2)

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The documentation shows use of sensitive credentials (`api_key`, `stream_key`) and immediately uses bearer-token authentication, but does not warn against logging, echoing, committing, or exposing those secrets in chat, screenshots, or client-side contexts. In an agent setting, this increases the chance that implementers mishandle long-lived credentials and accidentally leak control of the stream account.

Missing User Warnings

Medium

Confidence: 89% confidence
Finding: The skill enables actions that publicly start a livestream, post content, and read chat in real time, but does not clearly warn that these actions have public-broadcast and privacy consequences. In an agent context, this can cause unreviewed publication of generated content or collection/display of user chat without adequate operator awareness.

VirusTotal

52/52 vendors flagged this skill as clean.

View on VirusTotal