18th-Level AI Magic User 🧙♂️ Teaching developers to build secure software with AI https://xitter.twitterapi.xyz/t.co/p2rffkkHbC
Kauai, HI and Cobb, CA
Joined July 2009
- Tweets45.4K
- Following6.4K
- Followers17.6K
- Likes34.6K
Pinned Tweet
From my experience all software developers are now security engineers wether they know it, admit to it or do it. Your code is now the security of the org you work for. #GoldenAgeOfDefense – at Wat Ket, Thailand
Jim Manico from Manicode Security retweeted
I'm doing a webinar on secure AI coding on November 12. Please join!
manicode.com/webinar/
Jim Manico from Manicode Security retweeted
Threat modeling usually gets skipped because it's slow and the results aren't tied to your actual code. Grim Prompter from @manicode guides your AI coding agent through read-only repo inspection, with file-and-line citations for each finding. It has 36 workflows, STRIDE, PASTA, LINDDUN and attack trees, and works as a skill for Claude Code and Codex CLI. MIT licensed, with JSON baselines for change reviews.
Jim Manico from Manicode Security retweeted
We've given all Pro, Max, Ultra, and Team users one free full reset, across all models and limits. Use it anytime before December 10 at 2:00PM PT.
We recently fixed a few small issues that used more limits than intended, and the Fable resets didn't do much for those of you who'd already hit your weekly limits for all models. While these issues didn't affect everyone, we want to make up for the trouble.
You'll find it in Settings > Usage, or at clau.de/reset.
Jim Manico from Manicode Security retweeted
it can not be overstated how big of a deal this is.
aws.amazon.com/about-aws/wha…
Jim Manico from Manicode Security retweeted
In 1998, we at L0pht told the Senate software makers weren’t building security into products. 28 years later, users still pay for preventable flaws. Congrats to Lauren Zabierek & @boblord on launching the Software Safety Institute. Long overdue.
softwaresafety.org
Jim Manico from Manicode Security retweeted
As lower model versions are retired and higher ones replace them at similar costs, general AI safety will increase for organizations developing AI powered features.
Agent control though, because it’s nuanced and no one has solved sandboxing, will still be a huge attack vector.
Most real world attacks we’re pulling off these days require a mixture of skills: prompt injection, web pentesting, lpe, sandbox escape/exfil.
Time to become multi dimensional fam 🫶
The AI Assessment world isn’t Gandalf level anymore.
Jim Manico from Manicode Security retweeted
(I do have to say, I used to think the densest thing in the universe was a neutron star. Now I think it’s Marcus Hutchins.)
Jim Manico from Manicode Security retweeted
Agentic threat modeling is the way to go!
I built "Grim Prompter" to help developers put it into practice. It’s already getting a lot of traffic, and I’m thrilled to see the interest!
LINDDUN privacy threat modeling is supported today. Try this in Claude Code:
/threat-model deep web with LINDDUN PRO
I’m now expanding privacy coverage across the entire threat modeling lifecycle, from scoping and data flows to threat analysis, mitigations, and ongoing review. That includes broader coverage of GDPR, CCPA, and other privacy requirements.
Give it a try. Feedback and contributions are welcome!
github.com/jmanico/grim-prom…
Agentic threat modeling is the way to go!
I built "Grim Prompter" to help developers put it into practice. It’s already getting a lot of traffic, and I’m thrilled to see the interest!
LINDDUN privacy threat modeling is supported today. Try this in Claude Code:
/threat-model deep web with LINDDUN PRO
I’m now expanding privacy coverage across the entire threat modeling lifecycle, from scoping and data flows to threat analysis, mitigations, and ongoing review. That includes broader coverage of GDPR, CCPA, and other privacy requirements.
Give it a try. Feedback and contributions are welcome!
github.com/jmanico/grim-prom…
Hey InfoSec leads.
Stop debating which things to fix in your meetings and instead meet about fixing a lot of things.
#patchThePlanet
Jim Manico from Manicode Security retweeted
AI agents can now break into realistic enterprise networks on their own. A capability once limited to trusted-access programs is available to anyone.
Today we’re releasing Vals CyberOffense.
@willknight from @WIRED wrote an article about our work, link in the thread.
