Skillboss

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward AI gateway skill that sends user-provided prompts and its API key to a remote service, with a minor caution around downloading generated media files.

Install only if you trust SkillBoss/HeyBossAI with the API key and the prompts, text, image URLs, and context you submit. Treat returned media URLs as untrusted remote content: download only when you intend to, save to a safe location, and avoid sending secrets or sensitive internal data unless the provider’s privacy and retention terms are acceptable.

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: 92% confidence
Finding: The skill documentation explicitly instructs the agent to capture a URL from model output and fetch it with curl, writing the result to a local file, but it provides no warning or constraints around remote-content retrieval or filesystem writes. Because the URL is derived from an external service response, this can lead to unsafe downloads of untrusted content, accidental overwrites, or use of fetched artifacts by later steps without validation.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal