ClawHub
Back to skill

Security audit

Poyo Gpt 5 4

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed PoYo chat-completions helper that uses a user-provided API key only for user-directed requests.

Before installing, confirm you intend to use PoYo for chat completions and only run the submit script with payloads you are comfortable sending to that service. Keep POYO_API_KEY server-side and avoid enabling this skill to handle generic tasks unless you specifically want PoYo involved.

SkillSpector

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
90% confidence
Finding
The skill's invocation criteria are very broad, covering generic tasks like coding help, reasoning, summarization, and planning that overlap with normal assistant behavior. This can cause unintended activation and route user content or prompts toward an external API workflow when the user did not specifically request PoYo, increasing the risk of unnecessary data exposure or misuse of the configured API key.

Static analysis

No suspicious patterns detected.