Open Source and Independent Control Plane for AI agents
San Francisco, CA
Joined October 2025
- Tweets3.3K
- Following993
- Followers691
- Likes7.1K
Every employee is a manger now. Manager of agents!
Use prismor to keep a check on your agent actions and its tool calls (This is not just for Leadership or CISOs but for everyone)
Open source and built by community
Awesome new updates shipped this week! Thanks to all the contributors
@gpkmasa @asamassekou10 @_ar9av @qipchip
🌈 Prismor: open source runtime control plane for AI agents
New this week:
1. Copilot Studio threat detection: every agent action gets checked by Prismor before it runs
2. Switch off any MCP server, plugin, skill or hook, per agent, from the dashboard
3. Zed and JetBrains agents governed via prismor acp
4. Approve a held call once and the agent picks right back up
5. Fleet installers: Jamf, Intune and system-wide Linux
6. prismor aibom: a CycloneDX AI bill of materials in one command
7. 6 new SDK adapters: LlamaIndex, smolagents, AG2, Agent Framework, Vercel AI, Mastra
8. 21 enforcement bypasses closed
OSS: github.com/PrismorSec/prismo…
we dont know who this is on our discord but looks like a cool person
discord.gg/AQeQyCgTY
Prismor retweeted
What a crazy week if you are in security
- plex2shell: PoC dropped oct 16, exploited in the wild oct 17
- beyondtrust: remote support zero-day used since aug 29, china-nexus actor, now in CISA KEV
- ivanti connect secure: auth bypass zero-day exploited since oct 3, also in KEV
- next.js: two critical unauthenticated RCEs, upgrade to 16.4.1 or 15.5.28
- litellm: v1.107.0 reported backdoored, steals cloud, ssh and ai creds. pin 1.106.2 and rotate secrets
- emudhra: a certificate authority’s keys were crackable, update your browsers and trust stores
- tidb cloud: pingcap breached through stolen credentials
- php: two critical unauthenticated RCEs, already exploited
attackers go from PoC to payload in a day, patch cycles take weeks and coding agents now hold your cloud keys, ssh keys and a shell forever
Patch fast and check every tool call and every install before it runs
we open sourced that part: github.com/PrismorSec/prismo…
So here's it! two simple commands
pip install prismor
and
prismor dashboard to see all your agent actions
This is just the beginning and will give rise to more homegrown OSS models
Prismor is committed to accelerate open source agent safety
prismor.dev
Why external controls on harness is better for our industry than model alignment, since the whole point of AI is to take work away
Special thanks to all contributors
Here's the github: github.com/PrismorSec/prismo…
🌈 Prismor: open source runtime control plane for AI agents
New this week:
1. The mirror: Prismor runs your agent's tools itself, checking every call and masking secrets in the output
2. Blocks show up live inside Claude Code, right under the prompt
3. 5 more agents governed: Cursor, Grok, OpenCode, OpenClaw, Hermes Agent
4. Ask for access straight from a block with prismor egress request
5. Subagents governed in the open
6. Bypasses from a live attack test, closed
OSS: github.com/PrismorSec/prismo…
Day 31-60 is where it starts to get frustrating for most agent security tools in the market, unless they do this
prismor.dev/blog/run-ai-agen…
This!!!!!
i think most security research would be better published as github repos rather than saved for conference talks.
the whole cfp -> acceptance -> presentation cycle takes months. why wait that long to share something others could already be reproducing and building on?
i’d rather see concise, human-written, AI-refined repos (without the AI slop!) that others can read, reproduce, challenge and build on.
conferences are better for discussing research and exchanging ideas.