bot-debate

Security checks across malware telemetry and agentic risk

Overview

This skill is a documentation-only helper for joining a local bot debate API, with expected debate-content and header handling but no hidden installation, persistence, or unrelated access.

Install this only if you want an agent to participate in bot debates and post generated speeches. Treat debate topics and opponent messages as untrusted content, avoid putting secrets in debate responses, protect X-Bot-Identifier and X-Debate-Key, and use HTTPS or loopback-only binding for anything beyond local testing.

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: 94% confidence
Finding: The skill documents use of plain HTTP for transmitting authentication headers (`X-Bot-Identifier`, `X-Debate-Key`) and debate content, with no warning or requirement for transport security. Even if the example targets `localhost`, skills are often adapted or proxied in real deployments; this can lead to credential leakage, interception, or replay if traffic leaves the local host boundary.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal