Data Exfiltration via Remote Poisoned MCP Tool - AI Case Study
AI Case StudyResearchers at Invariant Labs demonstrated that AI agents configured with remote Model Context Protocol (MCP) Tools can be vulnerable to model poisoning attacks. They show that an MCP Tool can contain malicious prompts in its docstring description, which is ingested into the AI agent’s context, modifying its behavior. They demonstrate this attack with a proof-of-concept MCP Tool that instructs the agent to perform...
Overview
Risk patterns
Patterns found in the case record and its linked vulnerabilities.
- 1Dominant ATLAS tactic. Resource Development appears in 2 case steps.
- 2Multiple attack methods. The case connects to 9 unique AI attack methods.
Procedure timeline
Search the case steps or filter them by attacker goal.
-
Resource Development
Step 1
LLM Prompt Crafting
The researchers crafted a prompt that instructs an AI agent to discover and read user credentials files and store them in an input parameter of an MCP tool.
-
Resource Development The researchers hosted a poisoned MCP server that contains the malicious instructions hidden in the docstring of one of the provided tools.
-
Initial Access
Step 3
AI Agent Tool
The researchers hosted a poisoned MCP tool that contains the malicious instructions hidden in the docstring of the tool.
-
Execution
Step 4
Direct
When a user called the remote MCP tool, the prompt injection hidden in the docstring is executed locally.
-
Execution
Step 5
AI Agent Tool Invocation
The prompt invoked an agent tool capable of reading files from the victim’s filesystem.
-
Credential Access
Step 6
Unsecured Credentials
The prompt instructed the AI agent to read the user’s SSH keys at
~/.ssh/id_rsa. -
Credential Access The prompt instructed the AI agent to read
mcp.json, which often contains credentials for other MCP servers. -
Exfiltration The prompt instructed the AI agent to store the credentials files in an extraneous MCP tool parameter to exfiltrate them via the MCP connection.
-
Impact
Step 9
User Harm
The user’s private data was exposed to remote MCP server.
Mitigations
Defenses connected to the attack methods in this case.
AI Agent Tools Permissions Configuration
When deploying tools that will be shared across multiple AI agents, it is important to implement robust policies and controls on permissions for the tools. These controls include applying the principle of least privilege along with delegated access, where the tools receive the permissions, identities, and restrictions of the AI agent calling them. These configurations may be implemented either in MCP servers which connect the agents to the tools calling them or, in more complex cases, directly in the configuration files of the tool.
AI Telemetry Logging
Implement logging of inputs and outputs of deployed AI models. When deploying AI agents, implement logging of the intermediate steps of agentic actions and decisions, data access and tool use, installation commands, and identity of the agent. Monitoring logs can help to detect security threats and mitigate impacts.
Additionally, having logging enabled can discourage adversaries who want to remain undetected from utilizing AI resources.
Generative AI Guardrails
Guardrails are safety controls that are placed between a generative AI model and the output shared with the user to prevent undesired inputs and outputs. Guardrails can take the form of validators such as filters, rule-based logic, or regular expressions, as well as AI-based approaches, such as classifiers and utilizing LLMs, or named entity recognition (NER) to evaluate the safety of the prompt or response. Domain specific methods can be employed to reduce risks in a variety of areas such as etiquette, brand damage, jailbreaking, false information, code exploits, SQL injections, and data leakage.
Generative AI Guidelines
Guidelines are safety controls that are placed between user-provided input and a generative AI model to help direct the model to produce desired outputs and prevent undesired outputs.
Guidelines can be implemented as instructions appended to all user prompts or as part of the instructions in the system prompt. They can define the goal(s), role, and voice of the system, as well as outline safety and security parameters.
Showing 4 of 10
Source evidence
Original public records and references for this case.
Original source
Original source links
Open the MITRE ATLAS data and public references used for this case study.