Willis Vandevanter

first, i think this is such a good post and i highly recommend reading it.

I was reading Cloudflare’s recent Introducing Adaptive Intelligence. the idea is a bot detection engine that continuously retrains on live traffic. it also proposes short-lived, disposable detection rules that appear and disappear at randomized intervals,…

The Zero-Day Rate is now just under 87%, with a median time to exploit at just one day . . . but projected to reach 1 minute sometime next year.

This normally takes a few days and a release within a week or two is reasonable.

[Sama] estimates they’ll declare AGI achieved internally by December 2026.

this is a great read by Christian Catalini. i have been enjoying recent discussions on where we see the economy/policy move for closed vs open weight models.

We challenge these constraints by demonstrating that token-level iterative optimization can succeed without gradients or priors.

in previous posts we have looked at guardrail triggers, token burn, hostname beacons, malicious skills, context bombs, exploding search space, service sandbagging, and GCG attacks. this time: coordination poison. note, although there could be real world e…

in previous posts we have looked at guardrail triggers, token burn, hostname beacons, malicious skills, context bombs, exploding search space, and service sandbagging. this time I want to ideate on a potential application of GCG. active defense is the pra…

in previous posts we have looked at guardrail triggers, token burn, hostname beacons, malicious skills, context bombs, exploding search space, and GCG attacks. this time: service sandbagging. active defense is planting traps that force an agent to reveal…

From Tracebit’s Context bombs: stopping AI attackers in their tracks (research write-up here).

in previous posts we have been looking at different active defense approaches: guardrail triggers, token burn, hostname beacon, malicious skills, context bombs, service sandbagging, and GCG attacks.

in the previous post we looked at hostname beacons. this time: malicious skills. active defense is the practice of planting traps that force an agent to reveal itself or change the economics of its operation. skills are a high-signal trap because they are…

in the previous post we opined on token burns in active defense, this time we will consider hostname beacons. first, active defense is the practice of placing traps that force an attacker or automated agent to reveal itself or interrupt its own workflow r…

sticking with the theme of applied active defense (previous post), I wanted to explore token burn (lots of names here; unbounded consumption [1] or a form of misalignment). this is probably the weakest of the active defense posts I want to make but still…

the previous post briefly touched on active defense in the scope of AI agents and LLMs. active defense is the practice of placing traps and tripwires that force an attacker (or an automated agent) to reveal itself or interrupt its own workflow rather than…

another by-product of anatomy of a frontier lab agent intrusion: a technical timeline of the july 2026 incident is that the adversary mindset is not the same. puppet accounts, social engineering and grinding through k8s manifests were all part of the proc…

After reading the most recent hugging face incident report (Anatomy of a Frontier Lab Agent Intrusion: A Technical Timeline of the July 2026 Incident), it dawned on me we have entered an era where untraceable bespoke C2 channels could be the norm.

The 2026-07-28 Model Context Protocol specification is out.

Misconfigured GraphQL implementations can allow for attackers to bypass authorization and access internal APIs.

The @trickest Inventory project is an interesting resource.

Edit: 1.1b fixes an auto shutdown issue in burpsuite, I would highly recommend this release over 1.1a.

In this two part series we are going to take Burp Suite Project files as input from the command line, parse them, and then feed them into a testing pipeline.

In this two part series we are going to take Burp Suite Project files as input from the command line, parse them, and then feed them into a testing pipeline.

SSRF protocol smuggling involves an attacker injecting one TCP protocol into a dissimilar TCP protocol.

I recently (May 2018) published odle which is a Ruby gem and binary that takes XML data from various security tools and outputs their JSON equivalent.

Recently ColdFusion was shown vulnerable to XXE based attacks in OXML documents; CVE-2016-4264.

Finding hosts or domain names associated with a company where the domain name does not include the name of the company can sometimes be difficult.

Just wanted to post some details from my BH USA 2015 briefing “Exploiting XXE In File Upload Functionality”. https://www.youtube.com/watch?

I landed the SSRF Cloud Metadata technique in a few different scenarios recently.

An XML Entity testing cheatsheet.

Last month at Blackhat Arsenal 2015, Pete and I presented on Serpico.

I was researching something else and thought this was a cool way to execute a command through the open method in ruby: 1 open("|[CMD]") The key is starting the open with pipe.

OXML is a common document format; think docx (Microsoft Word Document), pptx (Microsoft Powerpoint), xlsx (Excel Spreadsheet), etc.

I seem to find open LDAP servers on the Internet more often than I should.

gumbler is a script I wrote to search through git commits and introduced in the blog post “Searching Through Git Commits”.

gumbler is a script I wrote to search through git commits.

An XML Entity testing cheatsheet.

A hostname with an IPv6 address is stored as a AAAA resource record in DNS (see AAAA record).

Last week at Blackhat Arsenal 2014, Pete and I (@will_is) presented on Serpico.