ClawHub
Back to skill

Security audit

SeggWat CLI

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward SeggWat CLI reference, with expected credential and data-management commands that users should handle carefully.

Install this only if you use SeggWat from the terminal. Verify the CLI package or installer before running it, prefer secret-manager or CI-secret injection for API keys, avoid inline tokens when possible, protect cached OAuth tokens, and review project and item IDs before running update, delete/archive, or automated CI commands.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger description is overly broad and explicitly says to activate on generic topics like feedback, ratings, NPS, helpful ratings, and CI/CD workflows, which can cause the skill to be invoked in conversations not actually requesting this specific CLI. Unintended invocation is dangerous because the agent may surface or encourage use of SeggWat commands, authentication flows, or automation steps in irrelevant contexts, increasing the chance of accidental data disclosure or inappropriate tool guidance.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The documentation includes raw API key usage both as an exported environment variable and as an inline command argument without warning about shell history, process-list exposure, log leakage, or accidental sharing. In a CLI/automation skill, this is more dangerous because users are likely to copy-paste examples directly into terminals, CI systems, or shared runbooks where secrets may be persisted or exposed.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal