Maay

Security checks across malware telemetry and agentic risk

Overview

This skill appears purpose-aligned for ATXP paid API access, but users should review it because it tells the agent to run unpinned external CLI code and source a local credential config file.

Install only if you trust the ATXP npm package and provider. Before use, confirm which ATXP account is loaded, expect paid usage or credit consumption, avoid sensitive prompts unless ATXP’s data handling is acceptable, and prefer a scoped environment variable export over broadly sourcing `~/.atxp/config` in a long-lived shell.

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: 89% confidence
Finding: The skill instructs users to inspect and then source a local credential-bearing config file (`source ~/.atxp/config`) into the current shell without any warning about secret exposure or shell-side effects. In an agent/skill context, this is risky because it normalizes loading sensitive environment data directly from disk and may expose credentials to logs, subprocesses, or later commands executed in the same session.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal