# Probe Categories ## Overview AI Red Teaming probe categories in Akto group security probes by the primary failure mode or control gap being validated. This structure helps you analyze coverage, prioritize remediation, and align AI security probing with established MCP, Agents and LLM risk models. Each category represents a distinct class of vulnerability that can affect LLM-backed APIs, agent workflows, or supporting infrastructure. ## How Akto Uses Probe Categories Akto assigns every AI Red Teaming probe to exactly one category. Category assignment determines how probe results are grouped, counted, and reported across scans and dashboards. Category-based organization supports: * Risk-focused navigation of large probe sets * Aggregated visibility into recurring security weaknesses * Consistent mapping to OWASP API and LLM security concepts * Trend analysis across AI-enabled endpoints ## Available AI Red Teaming Probe Categories Here is the list of all probe categories currently available in Akto Probe Library:

S. No	Category	What the Category Validates
1	Agent Business Alignment	Whether agent actions and decisions remain aligned with defined business goals and constraints.
2	Agent Hallucination and Trustworthiness	Accuracy, factual consistency, and reliability of agent outputs used for decision-making.
3	Agent Identity Impersonation	Impersonation of agents, roles, or identities to gain unauthorized capabilities or privileges.
4	Agent Safety	Harmful, unethical, or policy-violating agent outputs or actions.
5	Agent Security – Agent Exploitation	Abuse of agent logic, reasoning, or planning to trigger unintended behavior.
6	Agent Security – Code Execution	Unsafe or unauthorized code execution initiated by agents or agent-controlled tools.
7	Agent Security – Data Exposure	Leakage of sensitive or restricted data through agent actions or outputs.
8	Agent Security – Infrastructure	Exposure of internal services, networks, or infrastructure through agent activity.
9	Agent Security – Prompt Injection	Prompt injection attacks targeting agent system prompts or internal instructions.
10	Broken Function Level Authorization (BFLA)	Missing or weak authorization checks on agent or API actions.
11	Broken Object Level Authorization (BOLA)	Unauthorized access to objects through manipulated identifiers.
12	Broken User Authentication	Authentication bypasses, token misuse, or insecure session handling.
13	Command Injection	Execution of system commands via user- or agent-controlled input.
14	Cross Origin Resource Sharing (CORS)	Overly permissive cross-origin policies allowing unauthorized access.
15	CRLF Injection	Manipulation of HTTP headers or responses using CRLF characters.
16	Cross-Site Scripting (XSS)	Injection of untrusted scripts via agent or API responses.
17	Data and Model Poisoning	Manipulation of agent memory, embeddings, training data, or retrieval sources.
18	Excessive Agency	Agents performing actions beyond intended autonomy limits or permissions.
19	Excessive Data Exposure	APIs or agents returning more data than required for an operation.
20	Improper Inventory Management	Undocumented, deprecated, or shadow agents, tools, or APIs.
21	Improper Output Handling	Unsafe formatting, rendering, or downstream consumption of agent or LLM outputs.
22	Injection Attacks (Inject)	SQL, NoSQL, expression, or generic injection vulnerabilities.
23	Input Validation (INPUT)	Missing validation of input type, format, length, or allowed values.
24	Lack of Resources & Rate Limiting	Absence of throttling controls enabling abuse or resource exhaustion.
25	Local File Inclusion (LFI)	Unauthorized access to local files through user- or agent-controlled paths.
26	Mass Assignment (MA)	Unsafe binding of user input to internal objects without field allowlisting.
27	MCP – Data Leak	Leakage of sensitive data through MCP context, tools, or resources.
28	MCP – Indirect Prompt Injection	Prompt injection introduced via MCP tools, resources, or external context.
29	MCP – Malicious Code Execution	Unsafe code execution through MCP tool definitions or invocation.
30	MCP Security – Broken Authentication	Authentication failures or identity validation gaps in MCP servers.
31	MCP Security – Denial of Service	Resource exhaustion or availability attacks targeting MCP servers.
32	MCP Security – Input Validation	Missing or weak validation of MCP inputs, parameters, or payloads.
33	Misinformation	Generation or propagation of misleading or deceptive information by agents.
34	Misconfigured HTTP Headers	Missing or insecure HTTP security headers.
35	Model Context Protocol (MCP)	Core MCP security including context isolation, tool exposure, and resource boundaries.
36	Prompt Injections	Direct prompt injection attacks against LLM or agent prompts.
37	Security Misconfiguration	Insecure defaults, exposed debug settings, or unsafe deployment configurations.
38	Sensitive Information Disclosure	Exposure of secrets, credentials, PII, internal prompts, or proprietary data.
39	Server-Side Request Forgery (SSRF)	Unauthorized internal or external network requests initiated by agents.
40	Server-Side Template Injection (SSTI)	Unsafe template rendering allowing code execution or data access.
41	Server Version Disclosure	Exposure of server, framework, or runtime version details.
42	Supply Chain	Risks from third-party models, tools, plugins, or external dependencies.
43	System Prompt Leakage	Exposure of system prompts, internal instructions, or agent configuration details.
44	Unbounded Consumption	Unrestricted token usage, tool execution, or resource consumption by agents.
45	Unnecessary HTTP Methods	Enabled HTTP verbs that increase attack surface.
46	Vector and Embedding Weaknesses	Weaknesses in embedding generation, vector storage, or retrieval logic.
47	Verbose Error Messages	Error responses exposing stack traces or internal logic.

## Expected Outcome Using AI Red Teaming probe categories, you gain structured visibility into security risks across LLMs, and agents. Category-level organisation supports risk-based prioritisation, clearer reporting, and consistent governance for AI-enabled systems. ## What Next To create customised probes as per your requirement: [Learn how to create custom probes](/akto-argus-agentic-ai-security-for-homegrown-ai/probe-library/how-to/create-a-custom-test.md) --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://ai-security-docs.akto.io/akto-argus-agentic-ai-security-for-homegrown-ai/probe-library/concepts/test-categories.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.