Unverified50% confidenceCautionExact time
Carefully crafted prompts may induce a model to generate a UI tree that appears legitimate but submits form data to an attacker's server, with no way for the user to visually distinguish this.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIndirect prompt injection hides attack vectors in external documents or web pages read by the model, without the user's knowledge.77% similarUnverifiedIndirect prompt injection specifically refers to attackers carrying out attacks through external content that the model actively retrieves, making it more dangerous.76% similarUnverifiedAgents cannot naturally distinguish between data and instructions, which makes prompt injection threats particularly prominent in scenarios where agents browse the web or process user-uploaded content.74% similarUnverified工具调用使攻击面从让模型说错话升级为让模型做错事，危害从信息误导上升为实质性的数据访问和系统篡改72% similarUnverifiedAgainst self-generated prompt injection, traditional input filtering and source whitelisting defenses are nearly ineffective, requiring a redesign of validation mechanisms for model-generated content at the agent architecture level.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1000854API
curl https://kongchang.com/api/v1/knowledge/claims/1000854MCP
get_claim(id=1000854)