ClawHub
Back to skill

Security audit

Outlit

Security checks across malware telemetry and agentic risk

Overview

This is a coherent Outlit integration skill, but users should handle customer data and credentials carefully.

Install this only if you trust Outlit and want your agent to access customer intelligence data. Prefer npm or Homebrew over the curl-to-bash installer, use browser/OAuth or environment-based credential handling where possible, and only run integration setup or notification commands when you intentionally want those account-level actions.

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 includes example commands that place live-style secrets directly on the command line, such as API keys and service-role keys in JSON passed to `--config`. In agent and shell environments, command-line arguments are commonly exposed via shell history, process listings, logs, telemetry, and screenshots, so users may copy this unsafe pattern and inadvertently leak credentials.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.