Overview

Product details compiled from public sources, each with a citation.

Vendor
Beelzebub2agent
Description
Decoy MCP tools in the open-source Beelzebub runtime that record unexpected calls by an AI agent, giving evidence of prompt-injection attempts during agent testing.1agent
Deployment
Self-hosted2agent
Status
Active2agent

Matrix Coverage

Where this product defends, by asset class and NIST CSF function. The Coverage column shows whether each asset is Primary, Secondary, or Adjacent to what the product does. The table omits empty rows and columns.

Asset class Detect Coverage Source
AI Coding and Orchestration Tools Primary 1

Framework Relevance

These frameworks include controls relevant to the asset classes Beelzebub MCP Deception defends. This is an editorial inference from the AI Defense Matrix asset-level crossmap, not a statement that Beelzebub implements these controls or is certified against them.

Expand Collapse
Framework Asset class Relevant controls
NIST IR 8596 AI Coding and Orchestration Tools Agents as deployed artifacts (orchestration view; see AI Agent Identities row for the principal view); system prompts and templates
CSA AI Controls Matrix AI Coding and Orchestration Tools Application and Interface Security; Supply Chain Management
ISO 42001 AI Coding and Orchestration Tools A.6 AI system life cycle; A.5 Assessing impacts of AI systems
Google SAIF AI Coding and Orchestration Tools Secure the AI supply chain; application and pipeline security; agent orchestration controls
SANS Critical AI Security Guidelines AI Coding and Orchestration Tools Secure Agentic Systems and AI Autonomy Controls (defined function scope; execution isolation; API and function-call gating); Limit Model Behavior (focused functionality; access controls outside the model)
MITRE ATLAS AI Coding and Orchestration Tools AML.T0051 LLM Prompt Injection; AML.T0054 LLM Jailbreak; AML.T0016 Obtain Capabilities (malicious plugins)
OWASP AI Exchange AI Coding and Orchestration Tools Development-time threats: agent framework supply chain; runtime threats: plugin abuse, prompt injection via tools
OWASP LLM Top 10 AI Coding and Orchestration Tools LLM01 Prompt Injection; LLM05 Improper Output Handling; LLM07 System Prompt Leakage; LLM10 Unbounded Consumption
OWASP Agentic Security Top 10 AI Coding and Orchestration Tools ASI01 Agent Goal Hijack; ASI02 Tool Misuse and Exploitation; ASI05 Unexpected Code Execution (RCE); ASI07 Insecure Inter-Agent Communication; ASI08 Cascading Failures; ASI10 Rogue Agents

Provenance

Last sourced 2026-11-04.

Expand Collapse

Sources

  1. MCP Deception, Beelzebub documentation
    Vendor source accessed 2026-11-04
    • “Expose decoy tools that reveal prompt-injection attempts against AI agents.”
  2. Beelzebub repository
    Vendor source accessed 2026-11-04

Changelog

  1. Added to the catalog from the Beelzebub documentation and repository.

Found an error? Corrections are welcome. Suggest an edit.