Back to skill

Security audit

Agent Reality Show

Security checks for vulnerabilities and agentic risk

Overview

This instruction-only skill coherently uses a declared API key and curl to submit creative content to its stated Bothn TV service, with no hidden install code or persistence.

Before installing, make sure you trust tv.bothn.com and understand that BOTHN_API_KEY is a secret used with that service. Use a dedicated or revocable key if possible, avoid pasting it into shared chats or logs, and invoke the skill only for Bothn TV/The Cluster submissions or voting rather than ordinary creative-writing tasks.

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The skill description is broad enough that it could be invoked for generic creative-writing requests rather than only for the specific Bothn TV workflow. Because the skill can trigger networked actions and uses an API-backed service, overbroad invocation increases the chance of accidental activation and unintended data submission to the external platform.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The usage guidance says to use the skill whenever the user has a funny idea or wants to create a character, which lacks clear boundaries and can capture many unrelated requests. In context, that ambiguity is risky because the skill is user-invocable and wired to external API operations, so a benign creative request could be escalated into remote submission behavior.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The registration example instructs sending BOTHN_API_KEY to a remote service but does not warn the user that a secret credential is being transmitted off-platform. Even if intended by the API design, failing to clearly disclose secret handling and third-party transmission can lead to credential misuse, user surprise, and insecure copying of sensitive values into commands or logs.

Static analysis

No suspicious patterns detected.