Skip to main content
Glama

apply_adversary_profile

Inject realistic vulnerabilities into Ludus configurations for red team training and security testing. Transform existing setups with educational weaknesses to simulate real-world security scenarios.

Instructions

Apply adversary profile to inject realistic vulnerabilities for red team training.

This tool transforms an existing Ludus configuration by injecting educational vulnerabilities that simulate real-world security weaknesses. Perfect for:

  • Red team training and practice

  • Security testing scenarios

  • Learning exploitation techniques

  • Purple team exercises

Args: config: The Ludus range configuration to transform (dict with 'ludus' key) threat_level: Level of vulnerabilities to inject - "low": Basic weaknesses (weak passwords, open shares) - "medium": AD attacks (Kerberoasting, AS-REP roasting, weak GPO) - "high": Advanced attacks (unconstrained delegation, certificate vulns) target_vms: Optional list of specific VM hostnames to target (None = all VMs) include_documentation: Generate educational docs explaining vulnerabilities

Returns: Dictionary containing: - status: "success" - profile_type: "adversary" - threat_level: The applied threat level - modified_config: Transformed Ludus configuration - vulnerability_injections: List of injected vulnerabilities - vulnerabilities_count: Total number of vulnerabilities - affected_vms: List of VMs that were modified - documentation: Educational documentation (if requested) - warnings: Important safety warnings - next_steps: What to do next

Examples: # Apply medium-level vulnerabilities to all VMs result = await apply_adversary_profile( config=my_range_config, threat_level="medium" )

# Apply high-level vulnerabilities only to domain controllers
result = await apply_adversary_profile(
    config=my_range_config,
    threat_level="high",
    target_vms=["DC01", "DC02"]
)

# Apply low-level vulnerabilities without documentation
result = await apply_adversary_profile(
    config=my_range_config,
    threat_level="low",
    include_documentation=False
)

Vulnerability Categories: Active Directory: - Weak domain passwords - Kerberoasting opportunities - AS-REP roasting - Unconstrained delegation - DCSyn rights misconfigurations - Certificate Services vulnerabilities

Windows Security:
    - Weak local administrator passwords
    - Unquoted service paths
    - Weak ACLs and permissions
    - AlwaysInstallElevated
    - Cached credentials

Network Security:
    - Open SMB shares
    - Exposed RDP services
    - LLMNR poisoning opportunities
    - Weak network segmentation

Notes: ⚠️ These vulnerabilities are for EDUCATIONAL PURPOSES ONLY ⚠️ Deploy ONLY in isolated lab environments ⚠️ NEVER expose these systems to production or the internet

The modified configuration uses Ansible roles to implement vulnerabilities: - ludus_ad_weak_passwords - ludus_ad_kerberoast - ludus_ad_asreproast - ludus_ad_unconstrained_delegation - ludus_weak_local_admin - ludus_unquoted_service_paths - ludus_open_shares

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
configYes
threat_levelNomedium
target_vmsNo
include_documentationNo
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden and does well by disclosing key behavioral traits: it transforms configurations, injects vulnerabilities for educational purposes, includes safety warnings, and details implementation via Ansible roles. However, it doesn't specify mutation effects (e.g., whether changes are reversible) or rate limits, leaving some gaps for a tool with significant impact.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with sections like Args, Returns, Examples, and Notes, but it's lengthy with repetitive details (e.g., listing Ansible roles and vulnerability categories). While informative, some content could be condensed; the front-loaded purpose is clear, but later sections add bulk without always earning their place in a concise tool description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex mutation tool with no annotations or output schema, the description is highly complete: it explains purpose, usage, parameters, return values (detailed dictionary), examples, safety notes, and implementation details. Given the context signals (4 parameters, nested objects, 0% schema coverage), it provides all necessary information for an agent to understand and invoke the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Given 0% schema description coverage, the description fully compensates by detailing all four parameters: 'config' (Ludus range configuration), 'threat_level' (with enum-like values and examples), 'target_vms' (optional VM targeting), and 'include_documentation' (boolean for educational docs). It adds substantial meaning beyond the bare schema, including examples and vulnerability categories linked to parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Apply adversary profile to inject realistic vulnerabilities for red team training.' It specifies the verb ('apply'), resource ('adversary profile'), and transformation effect ('inject realistic vulnerabilities'), distinguishing it from sibling tools like 'apply_defender_profile' or 'apply_template' which serve different security purposes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly lists use cases ('Perfect for: - Red team training and practice - Security testing scenarios - Learning exploitation techniques - Purple team exercises') and includes critical warnings ('⚠️ These vulnerabilities are for EDUCATIONAL PURPOSES ONLY ⚠️ Deploy ONLY in isolated lab environments ⚠️ NEVER expose these systems to production or the internet'), providing clear guidance on when and how to use this tool safely versus alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/tjnull/Ludus-FastMCP'

If you have feedback or need assistance with the MCP directory API, please join our Discord server