ClawHub
Back to skill

Security audit

pruna

Security checks across malware telemetry and agentic risk

Overview

This is a coherent Pruna generative-media skill bundle that discloses API-key and media-tool use, with no artifact evidence of hidden execution, persistence, or unrelated data access.

Before installing, understand that using this suite may send prompts, uploaded media, and generated outputs to Pruna or Replicate and may consume paid API credits. Keep API keys scoped and private, and review the individual dependent skills before using workflows that make network calls or process sensitive media.

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 (1)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly instructs use of API credentials, curl, and upload/poll/download workflows against external services without clearly warning that user data, prompts, media, and tokens will be transmitted to third-party APIs. In an agent setting, this can lead to users or downstream tools sending sensitive content off-platform without informed consent, especially because the skill is framed as a recommended install and bundled workflow.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.