Unverified50% confidenceSolutionExact time
A common practice is to pass only the cleaned text of the current document and the structured fields extracted by code with each request, keep no session state across letters, and explicitly require in the prompt that "if the information is insufficient, state that it is unclear".
1
Sources
50%
Confidence
Long-term
Relevance
10/19/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe writable field set mechanism separately declares which fields are writable, and writes beyond the declared set should be rejected outright rather than truncated.70% similarUnverifiedInput filtering alone can hardly provide exhaustive defense against indirect prompt injection, because plausible-looking instructions can be naturally embedded in legitimate documents; a more reliable approach is to treat read content as untrusted and limit, at the tool call boundary, what follow-up actions it can trigger.68% similarUnverifiedSeparating the writing step from the browsing conversation and using a fresh prompt containing only the findings can prevent the model from citing unverified page text or fabricating information.67% similarUnverifiedWhen information needs to be passed to a downstream system for processing, it should not be crammed into one continuous block of text; structured output is the correct choice.66% similarUnverifiedLLM post-processing agents should have strictly constrained prompts that only perform spelling and grammar corrections within the scope of the given transcription text, preventing the completion of information that does not exist.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1069292API
curl https://kongchang.com/api/v1/knowledge/claims/1069292MCP
get_claim(id=1069292)