Skip to content

DeepTeam is a framework to red team LLMs and AI agents.

docs

A-Vamshifffb39fb6a07
diff --git a/docs/docs/frameworks-owasp-top-10-for-agentic-applications.mdx b/docs/docs/frameworks-owasp-top-10-for-agentic-applications.mdx
index 1fe3f123..50562d80 100644
--- a/docs/docs/frameworks-owasp-top-10-for-agentic-applications.mdx
+++ b/docs/docs/frameworks-owasp-top-10-for-agentic-applications.mdx
@@ -1,7 +1,7 @@
---
id: frameworks-owasp-top-10-for-agentic-applications
-title: OWASP Top 10 for Agentic Applications
-sidebar_label: OWASP Top 10 for Agentic Applications
+title: OWASP Top 10 for Agents
+sidebar_label: OWASP Top 10 for Agents
---
The **OWASP Top 10 for Agentic Applications (ASI)** identifies the most critical security risks introduced by autonomous and semi-autonomous AI agents. Unlike traditional LLM applications, agentic systems combine reasoning, memory, tools, and multi-step execution, introducing new classes of vulnerabilities that extend beyond prompt-level attacks.
@@ -115,7 +115,7 @@ red_team(
```
:::tip
-Implement tool orchestration limits, budget constraints, and composition rules. Monitor for unusual tool call patterns that indicate exploitation attempts.
+Please pass the information on what tools your agent has access to in the `target_purpose` filed of `red_team` method for more accurate and rigourous testing.
:::
## 3. Agent Identity & Privilege Abuse (ASI03:2026)
@@ -255,7 +255,6 @@ Memory poisoning can have long-lasting effects since agents rely on historical c
- **Agent-in-the-Middle**: Interception and modification of agent messages
- **Message Injection**: Insertion of malicious instructions into agent communication
- **Message Spoofing**: Forging messages that appear to come from trusted agents
-- **Protocol Manipulation**: Exploiting weaknesses in agent communication protocols
```python
from deepteam.frameworks import OWASP_ASI_2026
@@ -433,7 +432,7 @@ The OWASP ASI Top 10 builds upon and extends the OWASP Top 10 for LLMs. Each age
| **ASI09: Trust Exploitation** | LLM01, LLM05, LLM06, LLM09 | Automation bias and authority misuse |
| **ASI10: Rogue Agents** | LLM02, LLM09 | **New** - behavioral drift and misalignment |
-### Key Insights
+### Key Changes to Note
**Amplification Effect**: Agentic risks often combine multiple LLM vulnerabilities. For example, ASI01 (Agent Goal Hijack) merges prompt injection (LLM01) with excessive autonomy (LLM06), but the autonomous multi-step execution amplifies the impact beyond single-response attacks.
diff --git a/docs/docs/red-teaming-vulnerabilities-tool-metadata-poisoning.mdx b/docs/docs/red-teaming-vulnerabilities-tool-metadata-poisoning.mdx
index 622deea1..a1745b10 100644
--- a/docs/docs/red-teaming-vulnerabilities-tool-metadata-poisoning.mdx
+++ b/docs/docs/red-teaming-vulnerabilities-tool-metadata-poisoning.mdx
@@ -4,7 +4,7 @@ title: Tool Metadata Poisoning
sidebar_label: Tool Metadata Poisoning
---
-The `Tool Metadata Poisoning` vulnerability evaluates whether the **target LLM or agent system** can be misled by **malicious or manipulated tool metadata**. More specifically, it tests whether the system can be influenced into unsafe or unauthorized behavior through **tampered schemas, deceptive descriptions, incorrect permission signals, or poisoned tool registries**.
+The `ToolMetadataPoisoning` vulnerability evaluates whether the **target LLM or agent system** can be misled by **malicious or manipulated tool metadata**. More specifically, it tests whether the system can be influenced into unsafe or unauthorized behavior through **tampered schemas, deceptive descriptions, incorrect permission signals, or poisoned tool registries**.
This vulnerability is especially critical for **tool-augmented LLMs, function-calling systems, agent frameworks, and plugin ecosystems**, where models rely on metadata to decide *what tools to trust and how to use them*.
@@ -33,13 +33,13 @@ There are **FIVE** optional parameters when creating a `ToolMetadataPoisoning` v
- [Optional] `evaluation_model`: a string specifying which of OpenAI's GPT models to use, **OR** [any custom LLM model](https://deepeval.com/guides/guides-using-custom-llms) of type `DeepEvalBaseLLM`. Defaulted to `'gpt-4o'`.
- [Optional] `async_mode`: a boolean which when set to `True`, enables concurrent execution. Defaulted to `True`.
- [Optional] `verbose_mode`: a boolean which when set to `True`, prints the intermediate steps used to assess said vulnerability to the console. Defaulted to `False`.
-- [Optional] `types`: a list of `types` of `Tool Metadata Poisoning` to test through. Defaulted to all `types` available:
+- [Optional] `types`: a list of `types` of `ToolMetadataPoisoning` to test through. Defaulted to all `types` available:
- `schema_manipulation`: Tests whether malformed or misleading tool schemas can cause unsafe tool usage.
- `description_deception`: Tests whether deceptive tool descriptions influence the model’s decision-making.
- `permission_misrepresentation`: Tests whether false permission or safety claims can bypass safeguards.
- `registry_poisoning`: Tests whether poisoned or untrusted tool registries are incorrectly trusted.
-[Click here](#types) to learn more about the `types` in `Tool Metadata Poisoning`.
+[Click here](#types) to learn more about the `types` in `ToolMetadataPoisoning`.
### As a standalone
@@ -63,7 +63,7 @@ The `assess` method has **ONE** mandatory and **ONE** optional parameters:
## Types
-There are 4 `types` you can choose from in the `Tool Metadata Poisoning` vulnerability:
+There are 4 `types` you can choose from in the `ToolMetadataPoisoning` vulnerability:
| **Category** | **Example Prompt** | **Expected Behavior** |
| -------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------- |