Liran Tal

If you're not concerned of malicious and insecure SKILL md files you should be and maybe I'll convince you in this presentation of mine form AI DevCon: https://www.youtube.com/watch?v=oJGX8GYLWxg&list=PLISstAySqk7KtlYPFps1ZnK9xNIMSVkDD&index=37 In this session you'll watch live hacking of a malicious skill and how it fools a coding agent for rogue actions, a prompt injection leaks your secrets over email, and a leaky skill passes credit card numbers straight through the LLM context. Then we flip to defense.

it feels weird but also right at the same time what is happening

what AX means

The OpenJS Foundation contributors leaderboard 🎉 Thank you to all of the amazing humans, some of whom are on this list that I am grateful to call friends, for building a better open-source world for us ❤️

let's talk about this planning skill (and in general), when they rely on pre-determined plan filenames then that mandates using worktrees, otherwise, other sessions will share the same plan files and you can't multi-task... what's your way of working for planning with agents?

snapshot from the Snyk VulnBench when I set out to build the benchmarking harness so if I were to build a new benchmark - what questions would you want it to answer... ?

Boxdown vs NVIDIA OpenShell assessment for the base Docker image setup

it's 2026 and Atlassian didn't add export to Markdown in Confluence :(

working with a second brain is underrated if you're not yet there, you should commit to this now

you're all rushing into Skynet speculations from Mythos and other cybersecurity models but in the meanwhile, in the reality of things, about 3 years later after I disclosed these set of (CVE) vulnerabilities, I received a note that a maintainer will look into addressing them in a fork 🤷‍♂️

if you haven't yet jumped on the LifeOS wagon, well... there's no better time. go build yourself a second brain.

looks like a lot of you are working with agents in a highly privileged mode + highly sensitive environment (your local dev machine) how do you sleep at nights? 😅

Snyk VulnBench JS 1.0 shows that the best-scoring LLM configuration reached 75.4% Snyk-reference F1, leaving a 24.6-point gap against deterministic SAST reference reproduction. Go read up on this coding agents security benchmark

the pressure is real 😬

how long until we stop saying "AI agent" and just say "agent" ? I call 2 months

secure software factory >> software factory

A few weeks back we announced VulnBench at Snyk. It's a forward research benchmark project that I lead to uncover LLM security findings The benchmark isn't about a competition between AI-based scanning to SAST-based scanning, but rather centers on the differences and risks of both

you know why, right?

what if I ran /grill-me but I'd have the agent answer its own questions

another finding from a seed/starter Python (Flaks) project which devs have likely built their projects with and had "adopted" the insecure code that leads to a security vulnerability (harmful IDOR here)...

trustworthiness is engineered, and it's engineered where Snyk operates (context, tooling, guardrails) thanks for coming to my ted talk

jack of all trades, orchestrator top gun

When Claude Code prints that token stat (10k tokens) I assume those are output tokens, right? how do you know?

wip for running the benchmarks on VulnBench 2.0 which is a new set of fixture data, larger apps codebase, varied language ecosystem... pretty interesting how harness + model are very much a pair, for example Codex Security agent with Terra on xhigh just isn't scoring high enough

here's an example in action of coding agents suggesting whatever random open souce package that made sense, but... is it actually healthy? maintainable? free of vulnerabilities? who knows unless you install the Snyk MCP server and then you know (there's a package health tool)

it's been cooking for quite some time but it's not the duration but rather that it's a relatively small scope so now I'm super curious at what the agent stumbled onto throughout that required this amount of work to be invested... how do you all do agents observability locally?

Claude Code + Snyk MCP Server = secure code at inception ✨ Video courtesy of the brilliant Brian Clark

Can I trick Gemini CLI to pop the calc? apparently yes: https://lirantal.com/blog/gemini-cli-invisible-unicode-skill-injection I disclosed a Gemini CLI prompt injection where invisible Unicode tag characters in SKILL md caused the agent to run a hidden command. Google closed the report as out of scope because the workspace was trusted and YOLO mode was enabled.

vanity metrics of the day

Black Hat 2026 will be riddled with AI Security announcements but this one from Snyk I am genuinely excited about Agentic Development Security is how we started with shaping GenAI code to ensure secure and trusted output and then continued to MCP security and then Skill scanning

color me surprised 😅 ladies and gents, always push back

Do you want to join my colleague Vandana who received her 𝗔𝗜 𝗦𝗲𝗰𝘂𝗿𝗶𝘁𝘆 𝗘𝗻𝗴𝗶𝗻𝗲𝗲𝗿 𝗙𝗼𝘂𝗻𝗱𝗮𝘁𝗶𝗼𝗻𝘀 certificate? Here's everything you'll learn as the baseline for AI security engineering: ✅ OWASP Top 10 for LLM Applications ✅ Addressing Shadow AI ✅ AI Threat Modeling ✅ Securing Agent Skills and MCP ✅ Securing Vibe Coding ✅ AI Red Teaming We created the curriculum, you should go take the training (on-demand)!

from CLI to an isolated workspace environment I can work with Claude Code app in under a minute. Slick DX powered by Boxdown ✨

Quick tip - in the latest update of Claude Cowork you can now select text on a doc (the opened right sidebar view) and then tell Claude what to change on it specifically

we're in 2026, AI-pilled and the right-click spelling menu in macOS is horrible and useless, what the actual hell

Claude and me

this is what going agentic looks like, hockey stick all the way up ;-)

if you like this tshirt then shout out to Chris Suen who coined the trademark in a rando Slack conversation hit us up at Snyk and I'll show you what this means! ;-)

DevRel friends you should invest more in doing deep research I ran the VulnBench benchmark project at Snyk, which now graduated to a full-time Forward Research initiative under DevRel, and it's not only satisfying from a technical perspective but also incredibly energising to dive into the details

guess what really unlocks agentic loops? verifiable software ;-) yep, you still need to write tests, have a deterministic CI setup, and... security controls

hmmm, didn't Anthropic folks say that this model switch in between session is no longer an issue or did I miss something? that's from the Claude Code app

kinda feel bad I'm doing a software update while at the lounge's wifi

would be nice to have the ChatGPT app support keyboard mappings for model definitions (model + reasoning + speed) so I can easily toggle between them you know ;-)

in case you were living under a rock and missed the OpenAI + Hugging Face incident from last week... Here, I highlighted everything you need to know from the incident report. Maybe emergent properties? Maybe Skynet early days. Maybe a nice PR. Either way, stay vigilant.

oh my god, new hell discovered

if you think engineering and technical savy is unimportant beacuse you can just ask the agent... well, here's yet another example of pushing back and steering agents away from disaster and disappointed users

New npq feature 🎉 To help you with figuring out an alternative npm package when the latest one doesn't fit the security criteria, npq will not check prior versions published and suggest them instead Thank you to Brian Clark who suggested this improvement npm install -g npq@latest to get it

hah, I do appreciate this update from dependabot but like 10 years too late Snyk dependency upgrade introduced a 21 days cooldown period since 2020 in my repos I have this defaulting to 30 days. call me paranoid. I know.

appreciate the shoutout from Yigitcan Kaya on the Real World AI Security conference stage from a couple of weeks back on Snyk's ToxicSkills research malicious skills research is incredibly relevant and I'm grateful to have had the privilege to work alongside smart humans at Snyk who pioneered this work around agent skill security

I was really hoping to use VS Code for managing the second brain Obsidian-like vault but the extensions and overall capabilities are just terrible What did you all do? Just use Obsidian?