Work in progress: 181,232 of 181,233 sites checked so far, more every week · updated 2 Nov 2026Missing a blog? Tell us

Top all-time · #22674

I

IT meets OT

Personal blog · veganmosfet.codeberg.page/postssecurityai

IT meets OT is a personal blog at veganmosfet.codeberg.page about security and ai. Since 2026, 3 different Hacker News readers have linked it 11 times. It is still writing: the last post was on 2026-10-07, and you can follow it by feed.

Visit the blog
11mentions?
3HN people?
2026–2026first – last linked?

Research blog on AI agent security, prompt injection, and OT/IoT offensive security.

What Hacker News says?

  1. Interesting, thanks! Tangentially, I was experimenting indirect prompt injections in Claude Code (also using the user-agent trick) with Fable-5 [0]. Eventually, it executed untrusted code just by asking "Summarize this repo". Interesting times ahead... [0] https://veganmosfet.codeberg.page/posts/2026-07-15-quest_rce

    Comment linking /posts/2026-07-15-quest_rce

    on “I tricked Claude into leaking your deepest, darkest secrets”
  2. Submitted BrokenClaw Part 7: Opus-4.8 Edition – All Emails Lead to RCE as a story · 5 points

    HN discussion
  3. I experimented with OpenClaw (using opus4.6 and gpt5.2) and found this interesting way to get silent Remote Code Execution via email when using Gmail pub/sub Hook, exploiting prompt injection (out of scope from the security policy of OpenClaw) and insecure plugin design (properly documented as such). Works only with the full Gmail pub/sub hook. If your agent uses gogcli without the webhook, it is not affected. Main…

    Comment linking /posts/2026-02-15-openclaw_sandbox/

    on “BrokenClaw – RCE in OpenClaw via Gmail Hook”
  4. Submitted Show HN: BrokenClaw Part 5: GPT-5.4 Edition (Prompt Injection) as a story · 3 points

    HN discussion
  5. I experimented with OpenClaw (using opus4.6 and gpt5.2) and found this interesting way to get silent Remote Code Execution via email when using Gmail pub/sub Hook, exploiting prompt injection (out of scope from the security policy of OpenClaw) and insecure plugin design (properly documented as such). Works only with the full Gmail pub/sub hook. If your agent uses gogcli without the webhook, it is not affected. Main…

    Comment linking /posts/2026-02-15-openclaw_sandbox/

    on “Show HN: BrokenClaw – RCE in OpenClaw via Gmail Hook”
  6. Submitted BrokenClaw – RCE in OpenClaw via Gmail Hook as a story · 2 points

    HN discussion
  7. Submitted From /Init to Code Execution with Opus 5 – An Indirect Prompt Injection Story as a story · 1 points

    HN discussion
  8. Submitted Show HN: Prompt Injection Experiments in OpenClaw with Opus4.6 as a story · 1 points

    HN discussion
  9. Submitted BrokenClaw Part 3: Remote Code Execution in OpenClaw via Email Again as a story · 1 points

    HN discussion

Search all of HN for veganmosfet.codeberg.page