[HN Gopher] Heap Overflow in FFmpeg EXIF
       ___________________________________________________________________
        
       Heap Overflow in FFmpeg EXIF
        
       Author : retr0reg
       Score  : 71 points
       Date   : 2026-01-01 15:31 UTC (7 hours ago)
        
 (HTM) web link (bugs.pwno.io)
 (TXT) w3m dump (bugs.pwno.io)
        
       | ComputerGuru wrote:
       | Nice find.
       | 
       | (I don't see what this being reported during the Christmas
       | holidays has to do with not revealing the disclosure and patch
       | timeline, a "note that delays should be attributed to Christmas"
       | would have sufficed.)
        
       | rvz wrote:
       | > Pwno is a AI cybersecurity startup...
       | 
       | We all know that LLMs were used to find these vulnerabilities,
       | specifically on high impact projects. That's fine.
       | 
       | However, my only question is who actually provided the patch: The
       | maintainers of FFmpeg? The LLM that is being used? Or the
       | security researchers themselves after finding the issue?
       | 
       | It seems that these two statements about the issue are in
       | conflict:
       | 
       | > We found _and patched 6 memory vulnerabilities_ in FFmpeg in
       | two days.
       | 
       | > Dec, 2025: _avcodec /exif maintainer provided patch._
        
         | 9cb14c1ec0 wrote:
         | > We all know that LLMs were used to find these vulnerabilities
         | 
         | How do we know that? You seem quite certain.
        
           | hedgehog wrote:
           | They pitch their company as finding bugs "with AI". It's not
           | hard to point one of the coding agents at a repo URL and have
           | it find bugs even in code that's been in the wild for a long
           | time, looking at their list that looks likely to be what
           | they're doing.
        
             | bgwalter wrote:
             | The list is pretty short though for 8 months. ossfuzz has
             | found a lot more even with the fuzzers often not covering a
             | lot of the code base.
             | 
             | Manually paying _people_ to write fuzzers by hand would
             | yield a lot more and be less expensive than data centers
             | and burning money, but who wants to pay _people_ in 2026?
        
               | hedgehog wrote:
               | I can't speak to what exactly this team is doing but I
               | haven't seen any evidence that with-robot finds less bugs
               | than without-robot. I do have some experience in this
               | area.
        
               | tptacek wrote:
               | Bugs are not equivalently findable and different
               | techniques surface different bugs. The direct comparison
               | you're trying to draw here doesn't hold.
        
               | bgwalter wrote:
               | It does not matter what purported categories buffer
               | overflows are in when manual fuzzing finds 100 and "AI"
               | finds 5.
               | 
               | If Google gave open source projects $100,000 per year for
               | a competent QA person, it would cost less than this "AI"
               | money straw fire and produce better results. Maybe the QA
               | person would also find the 5 "AI" detected bugs.
        
               | tptacek wrote:
               | This would make sense if every memory corruption
               | vulnerability was equivalently exploitable, which is of
               | course not true. I think you'll find Google does in fact
               | fuzz ffmpeg, though.
        
               | bgwalter wrote:
               | Google gives a pittance even for full ossfuzz
               | integration. Which is why many projects just have the
               | bare minimum fuzz tests. My original point was that even
               | with these bare minimum tests ossfuzz has found way more
               | than "AI" has.
        
               | tptacek wrote:
               | Another weird assumption you've got here is that fuzzing
               | outcomes scale linearly with funding, which, no. Further,
               | the field of factory-scale fuzzing and triage is one
               | Google security engineers basically invented, so it's
               | especially odd to hold Google out as a bad actor here.
               | 
               | At any rate, Google didn't employ "AI" to find this
               | vulnerability, and Google fuzzing probably wouldn't have
               | outcompeted these researchers for this particular bug
               | (totally different methods of bugfinding), so it's really
               | hard to find a coherent point you'd be making about
               | "fuzzers", "AI", and "Google" here.
        
               | hedgehog wrote:
               | My guess is the main "AI" contribution here is to
               | automate some of the work around the actual fuzzing.
               | Setting up the test environment and harness, reading the
               | code + commit history + published vulns for similar
               | projects, identifying likely trouble spots, gathering
               | seed data, writing scripts to generate more seed data
               | reaching the identified trouble spots, adding
               | instrumentation to the target to detect conditions ASan
               | etc don't, writing PoC code, writing draft patches...
               | That's a lot of labor and the coding agents can do a
               | mediocre job of all of it for the cost of compute.
        
               | tptacek wrote:
               | If it's finding exploitable bugs prior factory-scale
               | fuzzing of ffmpeg hasn't, seems like a pretty big win to
               | me.
        
               | bgwalter wrote:
               | Try writing some software yourself and you'll understand.
               | But security "researchers" don't do that of course.
        
               | tptacek wrote:
               | I am a professional software developer and have been
               | since the 1990s.
        
         | tredre3 wrote:
         | PWNO provided a patch but it was rejected for being too
         | large[1]. A maintainer fixed it himself[2]. I don't know if
         | PWNO used a LLM but it seems clear that the maintainer had a
         | preferred specific style in mind so it was likely hand written
         | (albeit inspired by the initial patch).
         | 
         | 1. https://code.ffmpeg.org/FFmpeg/FFmpeg/pulls/21258
         | 
         | 2.
         | https://code.ffmpeg.org/FFmpeg/FFmpeg/commit/4bfac71ecd96488...
        
           | j1elo wrote:
           | I just need to say that "commits" has been translated to
           | Spanish as "confirmations" in that website, and it made me
           | chuckle.
           | 
           | Is Forgejo using LLM-assisted translations? Or simply somepne
           | without any context whatsoever in order to understand the
           | word's meaning?
           | 
           | ---- EDIT:
           | 
           | I went on a fun detour to inform myself better, and ended up
           | finding [1] where Gitlab had the same discussion. Seems some
           | translations have tried to use "confirmation" as translation
           | for a git commit.
           | 
           | But really, this is one of those cases where no local word is
           | able to appropriately describe such an unique concept oridea.
           | I'd love to retroactively chime in and _confirm_ (hah) that
           | the english word  "Commit" has trascended any translation
           | attempts, and absolutely nobody would know what you're
           | talking about if you say "confirmation" in an attempt to use
           | a spanish term.
           | 
           | So Forgejo authors if you read this: it'd better to do as
           | Gitlab did.
           | 
           | [1]: https://gitlab.com/gitlab-org/gitlab/-/issues/215956
        
       | renewiltord wrote:
       | Hmm interesting. You can see recent edits to the file here
       | https://github.com/FFmpeg/FFmpeg/commits/master/libavcodec/e...
       | 
       | This specific issue is fixed here
       | https://github.com/FFmpeg/FFmpeg/commit/4bfac71ecd96488dd2dc...
        
         | jeffbee wrote:
         | Well, maybe it does and maybe it doesn't. Since this commit
         | neither adds nor fixes any tests, we'll never know.
        
       | helge9210 wrote:
       | https://x.com/FFmpeg/status/2006773495066464580
       | 
       | > Seeing as this has made the orange site, let it be known this
       | person is a model security researcher.
       | 
       | > The issue was not in any FFmpeg release, and a report was sent
       | three days after a new code was added to FFmpeg Git.
       | 
       | > There was no big CVE ADVISORY "MUH SECURITEH" "you need to fix
       | this now or you will be hacked and the world will end" associated
       | with the report.
        
         | bgwalter wrote:
         | This is another drawback of security research, but one that had
         | already existed before "AI" with ossfuzz.
         | 
         | You basically cannot commit in public to the main branch and
         | audit and test everything 3 months before a release, because
         | any error can be picked up, will be publicized and go into the
         | official statistics.
        
           | nospice wrote:
           | > ... go into the official statistics.
           | 
           | There are no "official" statistics. None of this matters. If
           | we judged projects by the number of security holes they had,
           | then no one would be using ffmpeg, which had hundreds of
           | serious vulns.
           | 
           | Vulnerability research is useful insofar that the bad guys
           | are using the same techniques (e.g., the same fuzzing tools),
           | so any bugs you squash make it harder for others to attack
           | you. If your enemy is a nation state, they might still pack
           | your laptop / phone / pager with explosives, but the bar for
           | that is higher than popping your phone with a 0-day.
           | 
           | Vulnerability research is demonstrably _not_ useful for
           | improving the security of the ecosystem in the long haul.
           | That 's where sandboxing, hardening, and good engineering
           | hygiene come into play. If you're writing a browser or a
           | video decoder in C/C++, you're going to have exploitable
           | bugs.
        
             | toast0 wrote:
             | > Vulnerability research is demonstrably not useful for
             | improving the security of the ecosystem in the long haul.
             | That's where sandboxing, hardening, and good engineering
             | hygiene come into play. If you're writing a browser or a
             | video decoder in C/C++, you're going to have exploitable
             | bugs.
             | 
             | IMHO, vulnerability research is the stick that drives the
             | ecosystem towards all those things. Reports of
             | vulnerabilities in the codec for Rebel Assult videos (or
             | whatever) leads one to disable codecs other than those they
             | need. Reports of vulnerabilities in playlist support leads
             | one to disable playlist support where it's unnecessary and
             | run transcodes in a chroot sandbox with no network access.
             | Reports of buffer oveflows leads one to prefer
             | implementation in memory safe languages where available
             | with sufficient performance and also to sandbox when
             | possible.
        
               | tptacek wrote:
               | I mostly agree, and further would say that this doesn't
               | really conflict with the preceding comment.
        
         | GaryBluto wrote:
         | Is the FFmpeg Twitter account managed by a developer's teenage
         | son? No matter what point that they try convey, it's always
         | stated in an obnoxious manner.
        
           | bgwalter wrote:
           | Maybe they should hire Mario Nawfal for their announcements:
           | 
           | """ BREAKING: AI FOUND VULNERABILITY IN FFMPEG!
           | 
           | After decades of human struggle, humans no longer call the
           | shots.
           | 
           | Pwno decided to take the leap. They did not just find a
           | vulnerability---they found a BOMBSHELL! What took developers
           | weeks to write, AI analyzed in SECONDS! """
        
           | throawayonthe wrote:
           | it's kinda charming
        
       ___________________________________________________________________
       (page generated 2026-01-01 23:01 UTC)