ClawHub
Back to skill

Security audit

Gladia

Security checks across malware telemetry and agentic risk

Overview

This Gladia skill is a disclosed OOMOL connector wrapper for transcription management, including clearly labeled write and delete actions that require user confirmation.

Install this only if you intend to let Codex operate your connected Gladia account through OOMOL. Review any proposed start, upload, or delete action before approving it, and only run the one-time `oo` CLI installer if you trust OOMOL as the connector provider.

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
94% confidence
Finding
The invocation text is extremely broad: 'Use this skill for ANY Gladia request' and 'Whenever a task involves Gladia, use this skill instead of calling the API directly.' This can cause the agent to over-select the skill on loose keyword matches rather than clear user intent, increasing the chance of unintended reads, writes, or destructive operations through the connected account. The risk is amplified because the skill exposes state-changing and destructive actions, even though the document includes confirmation guidance.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.