Unverified50% confidenceSolutionExact time
Hidden characters and tags in MEMORY.md and recalled memories that mimic Claude Code's own markers are neutralized before being sent to the model, serving as a defense against prompt injection attacks.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/28/2026
First Seen
Valid until: 12/27/2026
Sources
Related Entities
Related Claims
UnverifiedClaude Code's memory mechanism is divided into two types: automatic memory and explicit memory management through the CLAUDE.md file.76% similarUnverifiedHermes provides a memory storage flag that, when set to False, retains no memory; it also provides a write approval flag to introduce a human-in-the-loop mechanism.72% similarUnverifiedThe core method for combating cognitive debt is to not copy and paste LLM-generated code, but instead to manually retype it word by word.68% similarUnverifiedWriting specifications as structured documents is essentially replacing uncertain memory recall with deterministic text injection.68% similarUnverifiedResearchers have found that hidden character techniques can be used to launch prompt injection attacks against large language models, embedding hidden instructions within normal text that the model will parse and execute.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/957228API
curl https://kongchang.com/api/v1/knowledge/claims/957228MCP
get_claim(id=957228)