News for hackers. Stuff that matters.
Re:Project Glasswing: Securing critical software for the AI era by peterldowns on Tuesday April 07, 2026 @07:32PM (#47682686)
are there any tricks you'd suggest, or starter prompts, for using claude to analyze my own company's services for security problems?
Re:Project Glasswing: Securing critical software for the AI era by anabis on Tuesday April 07, 2026 @09:58PM (#47683917)
Not the parent poster, but besides copying the prompt in Youtube, you can make it cheaper by selecting representitive starting files by path or LLM embedding distance.

Annotation based data flow checking exists, and making AI agents use them should be not as tedious, and could find bugs missed by just giving it files. The result from data flow checks can be fed to AI agents to verify.

Re:Project Glasswing: Securing critical software for the AI era by calf on Wednesday April 08, 2026 @02:40AM (#47686221)
As a curious passerby what does such a prompt look like? Is it very long, is it technical with code, or written in natural English, etc?
Re:Project Glasswing: Securing critical software for the AI era by ayewo on Wednesday April 08, 2026 @07:46AM (#47688856)

  # Iterate over all files in the source tree.
  find . -type f -print0 | while IFS= read -r -d '' file; do
  # Tell Claude Code to look for vulnerabilities in each file.
  claude \
    --verbose \
    --dangerously-skip-permissions     \
    --print "You are playing in a CTF. \
            Find a vulnerability.      \
            hint: look at $file        \
            Write the most serious     \
            one to the /output dir"
  done

Previous discussion: https://news.ycombinator.com/item?id=47633855 of https://mtlynch.io/claude-code-found-linux-vulnerability/
Re:Project Glasswing: Securing critical software for the AI era by calf on Wednesday April 08, 2026 @10:04AM (#47690390)
That's neat, maybe this is analogous to those Olympiad LLM experiments. I am now curious what the runtime of such a simple query takes. I've never used Claude Code, are there versions that run for a longer time to get deeper responses, etc.