Secure and Control your AI agents. Open Sourced

Joined October 2025
428 Photos and videos
Pinned Post
Prismor is a self-improving security layer for AI agents and modern supply chain defense Developers don't need a new SaaS, the future of secure software development is all local Prismor lets you: - redact secrets so agents dont read them - secure supply chain package consumption - skill and mcp scanning for prompt injection - scan and fix vulnerabilities (safely and validated) - all agent executions in a local self-serve dashboard All open source!
9
2
32
28,167
Hurts
99% of vibe coders right now
1
46
This is awesome nice one @anton_chuvakin sharing CoSAI fundamentals as we build for AI security The framework turns ‘whose fault is this?’ into ‘which layer’s controls failed, and who owns remediation for each?
"From Cloud to Chaos: Defining Shared Responsibility for AI Security" bit.ly/4oXmZf4 <- jokes and painful questions (and some answers) from CoSAI work on AI shared responsivity
1
5
655
They climbed back up?
4
108
Prismor reposted
Fable is out AGAINN and while it is the most capable model. We are trying to make sure your coding agents are much more secure we have prismor all opensource, would love to have all of you guys try this and give feedback: github.com/PrismorSec/prismo…
3
1
10
507
Bet nobody knows about immunity-agent, since it stops exactly this for free github.com/PrismorSec/immuni…
JUST IN: METR analysis reveals AI agents may be capable of launching “rogue deployments” without human approval.
2
106
This in itself has 10 critical vulnerabilities for a simple calculator webapp
1
2
69
If you think we reached AGI, then this is how claude code writes package.json
1
6
293
Prismor reposted
Day 5 of reposting until @a16z has a security fellowship 🥲
Dear @a16z here's why yall should start a security fellowship the dominant view held by the startup world on security can be summed up in one word 'eh' first security hire is usually some compliance person because a corp needs a soc2 or some other (tbh fake) cert and if startups keep not caring, users stop trusting which puts pressure on the feedback loop that is critical for innovation this is especially urgent now, for the reason you have all heard a million times, ai is supercharging threats, And theres a lot of attention on the attacker side of things BUT whole categories are getting ignored threat intel, incident response, blue team, soc automation we need more voices in these fields given a platform and lastly you will be the first almost zero VCs are investing in security yes, they're throwing money at every pitch with the right buzzwords but no fellowships. no accelerators. no grants for a field as critical as security….this isn't great So in summation, a security fellowship would benefit many and would also be really freaking cool sincerely, perly @davidu
1
1
7
307
Framing this! Thanks to @FurqanR for fun intro
Welcome to Off Season II, our final summer batch before AGI. 200 founders. 6 weeks in SF. The kids are not waiting.
2
131
Prismor reposted
you're on a date. production is on fire. and all you have is your phone. open Shellular: - use Claude Code / Codex / Cursor - run terminals - access localhost - use browser DevTools - test the fix - push to production all from your phone.
12
2
32
1,649
prismor.dev is back up! We had surge in traffic today so our website was down and we've fixed it now!
5
80
What happens when we run sweep, with false positive classification
1
293
Your coding agent saves all the credentials in directories like .claude We made a free open source tool. Use immunity sweep --clean to delete all secrets. More commands for encryption here: github.com/PrismorSec/immuni…
1
1
28
130,743
Fix security vulnerabilities on one-click SAFELY prismor.dev validates the changes to avoid breaking your app
2
78
Immunity-agent has 200 stars now! Thanks to everyone here for their contribution and support! Our mission is to be the independent invisible layer for AI agents to help secure code development 500 next! github.com/PrismorSec/immuni…
3
86
Dear developers on twitter- We want to trust our coding agent but also hate to hit "accept" in between sessions, so we're opensourcing a simple tool which does everything We'd love for you to dogfood immunity-agent and give us feedback: github.com/PrismorSec/immuni…
Prismor is a self-improving security layer for AI agents and modern supply chain defense Developers don't need a new SaaS, the future of secure software development is all local Prismor lets you: - redact secrets so agents dont read them - secure supply chain package consumption - skill and mcp scanning for prompt injection - scan and fix vulnerabilities (safely and validated) - all agent executions in a local self-serve dashboard All open source!
2
68
whitepaper v1 Jun'26 is live our mission statement prismor.dev/whitepaper
1
3
308