ClawHub
Back to skill

Security audit

Leonardo.Ai

Security checks across malware telemetry and agentic risk

Overview

This Leonardo.Ai skill is a coherent connector wrapper with disclosed account use and confirmation requirements for write actions.

Install this only if you intend to let the agent use your OOMOL-connected Leonardo.Ai account. Review any create_generation payload before approving it, since generation actions can spend credits or change account state, and only run the setup/login steps if the oo CLI or connection is actually missing.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The invocation text is overly broad: 'Use this skill for ANY Leonardo.Ai request' and 'Whenever a task involves Leonardo.Ai, use this skill instead of calling the API directly' can cause an agent to route any Leonardo-related mention into a tool-capable skill, even when the user did not ask to act. In a skill that includes write actions and shell execution via Bash, this increases the chance of unintended connector calls, schema probing, or account-state changes from ambiguous prompts.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.