PandaSt0rm (@PandaSt0rm) profile picture

Just a guy who loves fiddling with things he probably shouldn't... Also writes about some of those things :/ @HackTheBox_EU Academy

Earth
Joined May 2017
Conspiracy theory: The Chinese AI companies are removing the cyber stuff from their training data to prevent the global hardening mean being pushed up; since the American AI companies are restrictive even for defensive use they don't have a significant contribution to this end outside of some high profile commons. This allows the Chinese to then train private models with cyber included for the government which can then be used offensively on potentially uncovered/weakened targets.
25
Oof another one, this time in jsonc and can be chained to full privesc too
1
34
Worth noting that exploitation is extremely unrealistic, but not impossible
14
I'm very much unconvinced you need fancy tooling to wrap LLMs to be effective for red or blue teaming. I've yet to find something more efficient and effective than good workflows and skills in an agent like omp (oh-my-pi) or @opencode and a /goal
40
I'm up to 14 full RCE chains now, new one is in sqlite 🙃 at what point do you start making those cheesy "demos" or websites 😖
1
1
131
I'm sitting on so many full chain 0days I don't actually know what to do with myself... I miss the days of spending weeks to months tinkering on a single project, now I just have 100+ agents working on 10 different code bases and my brain feels like its permanently on fire... Its total mental overload 😩
20
You know... Last and this weekend I emailed (they wanted disclosure via email) a bunch of fully built and validated chains and patches to various linux projects which are nearly ubiquitous across the ecosystem. Some things kinda "holy shit holy shit holy shit patch yesterday" urgency. One has a "point at ip on the internet sometimes (like a 60% hit rate) get a shell" PoC attached. Yet to hear back from anyone :(
1
106
Kind of a funny comparison. Fully used my SuperGrok Heavy quota (was my last week, reset would have been in 3 days but i'm not renewing). Only ~1.5B tokens a week on Grok 4.7 for $1300 in equivalent API costs, vs $30 for nearly 4B DeepSeek tokens lol... Pretty much the same capability. DeepSeek was much faster too
1
1
42
Who started this "AI attacks run at machine speed" nonsense?
16
Holy trip down memory lane...
15
I swear fuzzing is worse than playing the slot machines. At least you can run out of money pulling that lever. With fuzzing: you gently caress the code to get it to tell you its secrets, you build the harness, you run it, waiting with baited breath. BRIGHT RED LETTERING POPS UP, YOU HAVE A CRASH. Triage starts. Adrenaline building... Its not exploitable, low impact... fuck we go again...
39
I don't get the hate against @GeminiApp It's been my goto model since argon went public, I prefer it even over opus 5.5. Argon is probably the first model that does better than the benchmarks indicate. GPT Sol 6.1 I won't let near my code bases anymore, it just wreaks absolute havoc. I know this is not a universal experience so its highly likely a side effect of either the languages i'm working in or the complexity of the work and my agent setups and skills. Opus 5.5 is okay, happy to give it a prompt and then background omp and come back a few hours later and check on it. I just don't personally like how claude writes code in general so not a huge fan. Argon I'm in love with. I can give it the vaguest of bugs and it will easily resolve them. It seems to just really *get* me and how I plan and architect projects. Rarely does it need to ask 30+ minutes of questions like opus does. I've yet to find a task I can't just toss at it and it will come back with a fully functional solution.
2
1
63
Never seen this one before
1
25
Bahahaha of course
14
I kinda wonder if this whole 'cyber restriction' thing going on in AI is a way to both create and then grab a pretty profitable market segment. From what I've heard companies are paying stupid amounts of money to be able to use glasswing models for eg. If the ai companies can pump up the specter of "we're all fucked because of AI" BUT with the fine print of "only if you dont secure your systems with our super cyber capable model" they're likely getting or going to be getting huge chunks of security budgets from orgs :/
25
It's kinda funny how argon keeps flagging *specifically* on objdump... tho in general I hope this isnt starting to shit towards a more restrictive model because it was not doing this a couple of days ago :/
18
Opus 5.5 Safe Guards just flagged on building an auth service in go... You cannot be serious....
50