ClawHub
Back to skill

Security audit

Poyo Sora 2 Pro

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward PoYo video-generation helper that clearly sends user-provided prompts and optional image or callback URLs to PoYo’s API using a PoYo API key.

Install only if you intend to use PoYo’s external API. Do not submit confidential prompts, private image URLs, or sensitive callback URLs unless PoYo’s privacy and retention terms fit your needs, and prefer setting POYO_API_KEY as an environment variable instead of passing it directly on the command line.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
85% confidence
Finding
The skill advertises shell-based execution via curl in metadata and instructions but does not declare corresponding permissions. That creates a capability/permission mismatch, which can bypass user expectations and security controls around command execution. In this context, the shell capability is used to send authenticated requests to an external API, so undeclared execution power increases the chance of unintended data transmission.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill instructs the agent to send Bearer-authenticated prompts and optional image URLs to a third-party service but does not include a clear user-facing disclosure or consent warning. Users may unknowingly transmit sensitive text, proprietary prompts, or private image references to an external provider, which is a privacy and data-governance risk.

VirusTotal

55/55 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.