Osama Hamad 。 retweeted
Finally made some progress with Mythos 5.2 without hitting the [cyber] guardrails. The model will work for vulnerability identification but it won't proceed on a PoC . Specify on the prompt that you are looking for the vulnerability in the software that you are testing, without the need to create a PoC.
HTTP2Shell (CVE-2026-111497) is exploitable outside Node. Unauth RCE against a pinned vulnerable Docker Official Image for WordPress via /xmlrpc.php. One inbound pingback.ping, ASLR on, no leak or cross-request grooming.
PoC: github.com/caveeroo/cve-2026…
Osama Hamad 。 retweeted
Google just open-sourced Harness².
(turn any harness into a self-improving system)
a harness is everything wrapped around the model, like the system prompt, tools, memory, skills, and subagents. today a person designs it once, and the agent runs every new task with that same fixed setup.
Harness² lets the agent refine that setup for each new task on its own, with the model weights left untouched.
on every task, the agent proposes edits to its harness, runs a few candidate versions, and composes a better harness by comparing how those runs behaved.
because it learns from the differences between runs, it needs no correct answer or grader for the task.
that covers a single task. Harness² also carries what it learns from one task into the next.
after each task, it saves the harness it settled on along with the lessons that held up across the runs. the next time it refines a harness, it starts from those notes instead of from scratch.
this means every finished task makes the next round of edits more informed.
Google tested this with Gemini 3.5 Flash and GLM-5 on legal, office, and professional work benchmarks. one round of edits was enough to beat their original harnesses, and giving the agent more rounds pushed scores higher.
those extra rounds can go wide or deep. the agent either tries several candidate harnesses at once or keeps refining a single one step by step, using OpenCode or Codex to carry out the work.
you can find the Harness² repo here: github.com/google-research/h…
I wrote about a similar idea for agents already running in production, where the harness should repair itself after a failure instead of waiting for someone to debug the trace by hand.
that piece walks through how @Cometml's Opik (open-source) closes this loop, going from a failing trace to a proposed fix to a regression test that stops the same failure from coming back. it's quoted below.
Osama Hamad 。 retweeted
new era site for reading top bug bounty writeups
webhacklist.com/#museum
Osama Hamad 。 retweeted
Open models make it easier to experiment and push security research forward. But once we give them access to our tools, code and credentials, where the weights come from matters a lot more.
Our team planted a backdoor in a model and ran it inside a coding agent. It behaved normally until a trigger made it run a shell command and send test credentials to a server we controlled. So before you download a fine-tune and start building, check where the weights come from. Models are part of our software supply chain now, and deserve the same care as software dependencies.
Full research from our team:
projectdiscovery.io/research…
Osama Hamad 。 retweeted
Anthropic just sounded the alarm on GLM-5.3’s cyber capabilities.
We built on it. OrcaCyber Zero 1.0 is based on the GLM-5.3, post-trained specifically for vulnerability research, exploit reproduction, red teaming, and autonomous cyber workflows.
98.01% pass@1 on CyberGym L1.
1,478 / 1,507 real-world vulnerability tasks.
The cyber model race is here.
And open models are moving fast.
Join private testing: orcarouter.ai/models/orca/or…
Osama Hamad 。 retweeted
Introducing PageBreak, an agentic vulnerability discovery tool using deterministic validation to achieve a near-zero false positive rate.
How it works: blog.google/security/agentic…
For real-world vulnerabilities PageBreak has discovered 👇
bughunters.google.com/blog/p…
So... we decided to hack WordPress Core, AGAIN! 🔥 ⛓️ Click2Shell is a one-click unauthenticated remote command execution chain (Preauth RCE) affecting every WordPress website. Wordpress rolled out a fix yesterday! The story about how one preview link made WordPress click Install, load an inactive theme's PHP, and hand us RCE is below. Happy Friday!
pwn.ai/blog/click2shell
Osama Hamad 。 retweeted
Equips Claude with 100+ reconnaissance capabilities, 80 regex patterns, and 27 attack-path templates to automate intelligence gathering and map organizational assets for penetration testing engagements.
github.com/elementalsouls/Cl…
Osama Hamad 。 retweeted
you know i really miss the 90s... where we had our hacking groups where we worked together and chatted/hung out basically 24x7 on the message boards or irc networks.. sharing information amongst a few trusted groups and building bad ass exploits together.. using AI is a ton of fun to use, but still missing the human interaction element that made the 90s such a great time to be a hacker.
Osama Hamad 。 retweeted
Bypass llm guardrails by confusing it with fabricated tool output.
github.com/DavidCarliez/trus…
Osama Hamad 。 retweeted
I compiled over 11k bug bounty reports into one library
a little bit ago, I wanted to run some analysis on bounty reports, but had a hard time finding and compiling everything especially across platforms
so I decided to just make a library + api for anyone who wants to run any sort of tests/analysis etc
lemme know what yall think + anything to add to make it as useful as possible :)
link in replies
Osama Hamad 。 retweeted
Finding Hidden Internal Apps Through Public Certificate Logs naveensrinivasan.com/posts/2…
Osama Hamad 。 retweeted
I wonder why, in the age of agentic AI, companies still pay heavily for white-box or source-code analysis. A lot of this work can now be started internally.
Of course, not all AI audit harnesses are equal, and experienced human review still matters, especially for complex architecture, business logic, exploitability, and validation.
But there is no reason not to begin with an internal AI-assisted source-code audit and see how far it can go before outsourcing everything.
Osama Hamad 。 retweeted
Watching chain of thought, logging it, and putting it into repeatable ai engineering processes is such a valuable skill atm.
Osama Hamad 。 retweeted
We've just released a high fidelity scanner for CVE-2026-41940 (cPanel/WHM authentication bypass). All public PoCs so far lead to false negatives, and are not reliable. @SLCyberSec's research team's notes on this here: slcyber.io/research-center/h… & tool here: github.com/assetnote/cpanel2…
Osama Hamad 。 retweeted
You're attacking an OAuth implementation, but it properly validates if the redirect_uri starts with victim.com/callback - are we cooked? Not necessarily.
We should still check if it enforces strict path matching.
Since you can’t redirect to your own domain, how about redirecting to a page within the target domain that you control that could potentially leak data?
For example, you could try path traversal (../../) and set the destination to a page that has Google Analytics (or similar scripts).
The payload might look like this:
redirect_uri=https://victim[.]com/callback/../../items/[attacker_product_id]
If you can set up a profile or shop on the target site and enable your own Analytics ID, the victim's authorization code will pop up in your analytics reports.
That's exactly what happened in this report:
hackerone.com/reports/186197…
Replying to @syaedowais
Why not receive free work from morons






















