[HN Gopher] OpenClaw: When AI Agents Get Full System Access. Sec...
___________________________________________________________________
OpenClaw: When AI Agents Get Full System Access. Security
nightmare?
Author : i-blis
Score : 19 points
Date : 2026-02-01 11:06 UTC (4 days ago)
(HTM) web link (innfactory.ai)
(TXT) w3m dump (innfactory.ai)
| chrisjj wrote:
| > LLM is Immune to Prompt Injection
|
| > Despite all advances:
|
| > * No large language model can reliably detect prompt injections
|
| Interesting isn't it, that we'd never say "No database manager
| can reliably detect SQL injections". And that the fact it is true
| is no problem at all.
|
| The difference is not because SQL is secure by design. It is
| because chatbot agents are insecure by design.
|
| I can't see chatbots getting parameterised querying soon. :)
| kaicianflone wrote:
| Is this where AgentSkills come into play as an abstraction
| layer?
| CuriouslyC wrote:
| A big part of the problem is that prompt injections are "meta"
| to the models, so model based detection is potentially getting
| scrambled by the injection as well. You need an analytic pass
| to flag/redact potential injections, a well aligned model
| should be robust at that point.
| niobe wrote:
| I would hope anyone with the knowledge and interest to run
| OpenClaw would already be mostly aware of the risks and potential
| solutions canvassed in this article, but I'd probably be shocked
| and disappointed.
| Forgeties79 wrote:
| There are definitely people I know who are talking about using
| it that I want nowhere near my keyboard
| dgxyz wrote:
| Yeah that. I had an external "security consultant" (trained
| monkey) tell me the other day that something fucking stupid
| we were doing was fine. There are many many people who should
| not be allowed near keyboards these days.
___________________________________________________________________
(page generated 2026-02-05 23:00 UTC)