Unverified50% confidenceFactExact time
The tags Simon Willison attached to that quote include security, generative-ai, ai-security-research and llms.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/22/2026
First Seen
Valid until: 11/5/2026
Sources
Related Entities
Related Claims
UnverifiedThe concept of prompt injection was first systematically proposed by security researcher Simon Willison in 2022, drawing an analogy to SQL injection attacks in traditional web security.64% similarVerifiedPrompt injection attacks were first publicly demonstrated by security researcher Riley Goodside in 2022 and have been listed by OWASP as the top security risk for LLM applications.63% similarUnverifiedExisting LLM security testing resources fall into three categories: attack prompt libraries, red-teaming frameworks, and data desensitization/synthesis tools.62% similarUnverifiedPrompt Injection attacks were first systematically described by security researcher Riley Goodside in 2022; the root cause is that LLMs cannot distinguish at the semantic level between system instructions, user instructions, and external data content.60% similarUnverifiedSimon Willison published the release notes on the official Datasette blog and categorized it as a security release.58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1086120API
curl https://kongchang.com/api/v1/knowledge/claims/1086120MCP
get_claim(id=1086120)