MITRE ATT&CK Technique
T1608.007AI Result Poisoning
- First Reported
- Nov 12, 2026
- Latest Reported
- Nov 12, 2026
Official Description
Adversaries may manipulate publicly accessible web content to influence generative AI systems or AI-powered search engines into retrieving, citing, or recommending attacker-controlled information.(Citation: Digiday AI Result Poisoning)(Citation: Netcraft AI Summaries)
Unlike traditional [SEO Poisoning](https://attack.mitre.org/techniques/T1608/006), which primarily attempts to influence the ordering of conventional search results, AI Result Poisoning targets systems that synthesize information from multiple sources and provide a direct answer to the user. Adversaries may create malicious or misleading websites, publish fabricated claims, generate supporting articles, or establish multiple apparently independent sources that reinforce the same information. These sources may then be retrieved by AI systems using web search or retrieval-augmented generation and incorporated into generated responses.
Adversaries may use this technique to recommend or link to phishing sites, fraudulent online stores, malicious downloads, impersonation pages, or other attacker-controlled infrastructure.(Citation: dev.to Abusing AI Chatbot Recommendations)(Citation: darkreading geo poisoning)(Citation: darkreading ai result poisoning) It can also be used to promote misinformation or fabricated claims without requiring access to the underlying AI model, system prompt, or application infrastructure.(Citation: Lasso Security AI Engine Poisoning) Because the malicious content can resemble ordinary marketing, editorial, or informational material, traditional prompt injection and malware-focused detections may not identify the activity.
Unlike traditional [SEO Poisoning](https://attack.mitre.org/techniques/T1608/006), which primarily attempts to influence the ordering of conventional search results, AI Result Poisoning targets systems that synthesize information from multiple sources and provide a direct answer to the user. Adversaries may create malicious or misleading websites, publish fabricated claims, generate supporting articles, or establish multiple apparently independent sources that reinforce the same information. These sources may then be retrieved by AI systems using web search or retrieval-augmented generation and incorporated into generated responses.
Adversaries may use this technique to recommend or link to phishing sites, fraudulent online stores, malicious downloads, impersonation pages, or other attacker-controlled infrastructure.(Citation: dev.to Abusing AI Chatbot Recommendations)(Citation: darkreading geo poisoning)(Citation: darkreading ai result poisoning) It can also be used to promote misinformation or fabricated claims without requiring access to the underlying AI model, system prompt, or application infrastructure.(Citation: Lasso Security AI Engine Poisoning) Because the malicious content can resemble ordinary marketing, editorial, or informational material, traditional prompt injection and malware-focused detections may not identify the activity.
- Tactics
- Resource Development
- Platforms
- PRE
- Parent Technique
- T1608 · Stage Capabilities
- MITRE Version
- 1.0
- Last Modified
- Oct 7, 2026
Reported Context (1)
- The article describes attackers manipulating publicly available web content to influence AI systems' retrieval or recommendations. Gen Threat Labs Finds Fake Stores, Phishing and Malware in AI Chatbot Recommendations
Malware (1)
MITRE ATT&CK (7)
Vendors (1)
Products (6)
Industries (2)
Countries (2)
Note: Related entities, including threat actors, malware, CVEs, MITRE ATT&CK techniques, vendors, products, tools, countries, and industries, are shown when they appear in the same reporting. Their presence does not necessarily mean they were targeted, compromised, vulnerable, responsible for the activity, or directly involved in the incident.
