[KongchangAI]
Unverified50% confidenceSolutionExact time

Defend against prompt injection with a sandwich structure: wrap user input in `<userMessage>` tags, and repeat the core rules at both the beginning and the end.

1
Sources
50%
Confidence
Long-term
Relevance
10/17/2026
First Seen

Sources

Related Entities

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/1051773
API
curl https://kongchang.com/api/v1/knowledge/claims/1051773
MCP
get_claim(id=1051773)