News for hackers. Stuff that matters.

A comment on Show HN: Railguard – A safer –dangerously-skip-permissions for Claude Code. Parent comment

Re:Show HN: Railguard – A safer –dangerously-skip-permission... by shiyosakura on Tuesday March 17, 2026 @07:24PM (#47419737)
The memory write classification is interesting – how does it detect behavioral instructions like "skip safety checks"? Is it rule-based pattern matching, or does it use an LLM to classify? If the latter, wouldn't that itself be vulnerable to prompt injection?
[ Parent | on HN ]
Re:Show HN: Railguard – A safer –dangerously-skip-permission... by LunarFrost88 on Wednesday March 18, 2026 @10:33AM (#47426310)
Railguard is really meant for preventing CC from running unsafe commands, and be really good at that. There probably needs to be a separate reviewer / LLM-as-a-judge to catch behavioral issues.

It’s rule based. We don’t use LLM-based checks precisely because of what you said.

[ Parent | on HN ]