HN Explorer

timstark

↗ HN profile [ 430 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Show HN: MCP server that strips injection vectors from LLM input (github.com)

    also cuts tokens 93% Claude Code's WebFetch converts HTML to markdown and runs it through a secondary model before it hits your context — but that pipeline wasn't designed as a security boundary. Turndown strips…

    2 points 0
  2. Show HN: I solved Claude Code's prompt injection problem, saved tokens doing it (github.com)

    I built a drop-in MCP server that sanitizes web content before it reaches your LLM — stripping prompt injection vectors deterministically, no LLM call needed. Along the way I found it also cuts token usage by ~90%.…

    1 points 1
  3. Show HN: Trawlx - Tweet text, likes, and retweets as JSON, no API keys (github.com)
    5 points 2