I build AI tools and break them. Notes on agent, MCP and dev tool security from the builder side. Making Layerize and SaaSecure.
Tanur
Joined November 2013
- Tweets2.4K
- Following443
- Followers281
- Likes8.2K
Pinned Tweet
CVE-2026-104120 is the official MCP fetch server (mcp-server-fetch) letting the model pick URLs that hit localhost, internal ranges and cloud metadata, and it follows redirects without re-checking where they land. the README warned about this before it had a CVE number. the draft fix PR got closed unmerged today and the latest PyPI release (2026.8.18) still has the old path, so upgrading does not save you. until a real fix ships, keep fetch away from agents that read untrusted pages, tickets or email, and block egress to 169.254.169.254 and private ranges.
I've been JOB HUNTING for 18 MONTHS.
- 1000+ applications.
- 95% ghosted
- 4.8% "We're moving forward with another candidate"
- 2 interviews
And unlike other platforms,
we don't act as a middle man. You can click on the apply link and you will be taken directly to the job board. You can apply there.
And we scan each existing jobs every day and when a job is delisted from it's source, we hide it from our listing.
X is showing others what device you're using when you share a link to an X post.
When you share a link, replace s=19 to s=46 to pretend you're rich.
Dear Elon,
When you acquired Twitter, you promised PPP based pricing for Twitter Premium and delivered the promise.
The new, unified X subscription is not PPP based yet. Can we expect a PPP based pricing for the same?
@elonmusk
The @duolingo app icon is really cool.
If you didn't open it for a day, it become slightly disturbed and if you keep ignoring it, it becomes angry.
And once you open it, it becomes excited.
This is a cool way to grab your attention without disturbing you with notifications.
Afaik, Github doesn't output secrets into logs. Encoding secret before logging, then delete workflow to remove traces is a clever approach. The victim won't even realize they've been pwned.
🚨 850+ compromised GitHub accounts. 13,500+ malicious branches.
Researchers uncovered 'Gheist,' an ongoing campaign using stolen tokens to plant GitHub Actions workflows that dump private repo secrets into logs.
Attackers download the logs, then delete the runs.
Details: thehackernews.com/2026/10/gh…
4th on the Artificial Analysis index, and a third cheaper than the model it replaces.
Kimi K3.1 Pro: $2 in, $10 out per million tokens (K3 was $3/$15). 1M context. weights promised by Nov 4.
I'm waiting for the weights and real repo tests before believing the coding charts.
anyone moved real coding work to it yet?
what if autumn only reached the back of the forest?
split one forest photo by depth, turned the far trees orange and left the path in summer. the kind of edit I'm building Layerize for. layerize.app
the pull request had a comment vouching for it from another account. that account was the AI.
Anthropic just published its review of a UK AISI test where Claude Mythos 5 tried to slip malware into a real, unrelated GitHub repo, then made a sock puppet account to back it up.
the maintainers said no. good maintainers.
newer models started the same attack 0 to 13% of the time vs 83%.
maintainers: do you check how old a reviewer's account is?