Unverified50% confidenceFactExact time
Prompt injection is caused by untrusted content in the context (such as instructions in web pages or emails), and the model has no reliable way to distinguish instructions from data, which is a direct consequence of everything being just tokens in the same window.
1
Sources
50%
Confidence
Long-term
Relevance
10/14/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedPrompt injection is essentially an instruction hijacking attack that exploits the structural flaw of LLMs being unable to distinguish system instructions from user data at the semantic level, and is conceptually similar to SQL injection.77% similarUnverifiedIndirect prompt injection hides attack vectors in external documents or web pages read by the model, without the user's knowledge.75% 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.75% 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.70% similarUnverifiedPrompt injection attacks do not need to exploit software vulnerabilities; they exploit the model's difficulty in distinguishing instructions from data.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1027111API
curl https://kongchang.com/api/v1/knowledge/claims/1027111MCP
get_claim(id=1027111)