ClawHub
Back to skill

Security audit

narrate-video

Security checks across malware telemetry and agentic risk

Overview

This appears to be a disclosed text-to-speech helper that uses an Inworld API key, with the main caution being broad activation wording and normal credential handling.

Install only if you are comfortable storing an Inworld API key locally and sending the text you synthesize to Inworld.ai. Use it for narration or text-to-speech tasks, and clarify requests involving music, sound effects, or adding/muxing audio into video before running it.

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
86% confidence
Finding
The trigger phrases are broad enough to match generic requests like adding audio or sound to a video, which could cause this skill to activate outside its intended workflow. Over-broad activation can unexpectedly route benign requests into a privileged workflow that performs shell operations and accesses credentials, expanding attack surface through unnecessary invocation.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal