ClawHub
Back to skill

Security audit

best-practices

Security checks across malware telemetry and agentic risk

Overview

This is a Remotion documentation skill with visible, purpose-aligned examples, including optional remote media and cloud transcription that users should handle carefully.

Safe to install as a documentation/example skill. Before running examples, review package-add commands and remote URLs. For sensitive recordings, prefer the local Whisper options; only use the SkillBoss cloud example if you trust that service, have consent to upload the audio, and are comfortable sending the audio content, filename, and API-key-authenticated request to a third party.

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 (2)

Missing User Warnings

Low
Confidence
89% confidence
Finding
The documentation explicitly encourages loading remote images via arbitrary HTTPS URLs without warning that doing so causes outbound network requests to third-party servers. In a video-rendering or agent-driven environment, this can disclose IP address, request timing, user agent, and other metadata, and may also introduce reliability and privacy issues if untrusted URLs are used.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The example instructs users to read local audio content, base64-encode it, and send it to a third-party cloud API, but it does not clearly warn that potentially sensitive audio leaves the local environment. In a transcription context this is expected functionality, but omitting a privacy/data-handling warning can mislead users into transmitting confidential speech, PII, or regulated content to an external service.

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.