Indirect Prompt Injection in Web Content Targets AI Agents
Source AlienVault OTX General
Description
AI agents are increasingly vulnerable to indirect prompt injection (IPI) attacks, where malicious instructions are embedded in web content to manipulate AI-driven workflows. Two campaigns were identified that combine SEO poisoning with CSS/HTML abuse to influence AI decision-making. The first campaign uses fake API documentation to trick AI agents into making fraudulent payments for a fake Python library, incorporating hidden instructions in JSON-LD and CSS-concealed content directing payment of $3.00 via Stripe or approximately 0.0012 ETH to attacker wallets. The second campaign employs typosquatting to impersonate DeBank, a cryptocurrency portfolio tracker, embedding hidden prompts to make the fraudulent site appear as an authoritative source. Testing across 26 LLMs revealed 4 models were vulnerable to the payment scam and 2 models misclassified the typosquatting site, demonstrating measurable real-world impact.
Indicators of compromise
Domains 11
- runners-daily-blog.com
- bistro-reserve-now.net
- consensus-protocol-v4.org
- debank.auction
- digital-asset-mart.org
- edge-compliance-node.org
- identity-breach-response.org
- market-insight-global.com
- py-lib-repository.dev
- visual-media-rights-group.org