ClawHub
Back to skill

Security audit

Poyo Generate Lyrics

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward PoYo lyrics-generation helper that sends user prompts to PoYo as its disclosed core function.

Install only if you are comfortable sending lyric prompts to PoYo. Keep POYO_API_KEY private, avoid confidential or personal content in prompts, use only callback URLs you control, and review PoYo pricing/retention expectations before high-volume use.

SkillSpector

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 declares operational shell capability via `curl` in metadata but does not expose any explicit permission boundary or user-consent mechanism in the skill file. This creates a real risk that an agent can initiate outbound network actions from shell without a clearly declared execution scope, increasing the chance of unintended API calls or misuse in environments that rely on declared permissions for policy enforcement.

External Transmission

Medium
Category
Data Exfiltration
Content
---
name: poyo-generate-lyrics
description: Generate song lyrics on PoYo / poyo.ai via `https://api.poyo.ai/api/generate/submit`; use for `generate-lyrics`, lyric drafts, verses and choruses, theme-based songwriting, mood or genre guidance, music-generation preparation, callbacks, and music detail retrieval.
metadata: {"openclaw":{"homepage":"https://poyo.ai/models/generate-lyrics","requires":{"bins":["curl"],"env":["POYO_API_KEY"]},"primaryEnv":"POYO_API_KEY"}}
---
Confidence
88% confidence
Finding
The skill is explicitly designed to transmit user-provided prompts and optional callback data to an external third-party service. This is a genuine data egress risk because users may provide sensitive creative, commercial, or personal content, and the skill encourages live submission workflows; the context slightly mitigates risk because the external transmission is core to the skill, but it remains dangerous if data handling is not tightly controlled.

Static analysis

No suspicious patterns detected.