Datadog built an AI-powered 'judge' using LLMs to evaluate whether code and agent skills are malicious in intent — and found malicious skills across multiple marketplaces.
Where this was said
At 7:44 · chapter starts 5:40
The lesson from the SQL incident translated directly into architectural changes. Datadog built role-based MCP servers — dedicated servers scoped to specific functions like SDRs — that govern exactly what data an AI agent can retrieve based on the user's role [1] — Emilio Escobar "Rather than locking down data broadly, Datadog built role-based MCP servers that give AI agents access to exactly the data their user's rol…" 05:30 . Once that governance layer is in place, employees can use whatever AI tool they prefer. On the engineering side, the challenge was different: how do you let coding agents authenticate to services like GitHub or AWS without exposing static credential files? Datadog contributed to an open-source sandbox that solves this by design — agents simply cannot access credential files in the home directory [2] — Emilio Escobar "Static credential files in a home directory are a ticking time bomb for AI coding agents. Datadog's sandbox solution injects credentials ep…" 06:30 . Instead, credentials are injected ephemerally at the exact moment an agent needs them, using an existing CLI tool. The agent calls a 'auth GitHub' function, receives a short-lived token, does its work, and the token disappears. No persistent secrets, no exfiltration surface.
Datadog's sandbox prevents agents from accessing static credential files; instead, credentials are injected ephemerally at the moment an agent needs them.
Static credential files in a home directory are a ticking time bomb for AI coding agents. Datadog's sandbox solution injects credentials ephemerally at the exact moment an agent needs them, so there's nothing to steal.
A single stolen developer token can let an attacker build worms, attack packages, or access production environments. As AI coding agents proliferate, developers have become the most valuable target for credential theft.
Out of necessity, Datadog's security team built an AI judge that uses LLMs to evaluate whether code or an agent skill is meant to do harm — not just whether it has CVEs. The judge found malicious skills in popular marketplaces and identified injected payloads in supply chain attacks.
Quickly forming opinions on how the Twitter algorithm and platform worked allowed the speaker to grow rapidly on the platform.
Sam's initial MVP was coded in approximately one week using ChatGPT voice mode and copy-pasting code, with no prior technical experience.
Sam argues Discord is 10x better than email for building relationships with younger users who rarely check their inbox.
Sam's monthly operating costs include Cursor ($200), AI image generation ($100), AI video generation ($200), hosting ($100), email marketing ($80), and AI compute ($300–$500).
Sam recommends copying days of Discord chat history into ChatGPT and prompting it to list recurring pain points as a fast, free market research technique.
Bhanu and his team built approximately 50 free tools to attract search traffic, each linked back to SiteGPT.
With AI coding tools like Cursor, Bhanu can now create a new free marketing tool in less than 5 minutes by referencing existing tools.
Bhanu filters Ahrefs keyword results to show only those with a keyword difficulty below 10, making them realistic ranking targets for any decent website.
Bhanu sets a minimum search volume of 1,000 monthly searches when selecting keywords to target with free tools.
We use essential and analytics cookies to run Vuci. To understand how the site is used: Privacy Policy.
Install Vuci on your phone
Add it to your home screen for a faster, app-like experience.
Install Vuci on your phone
Tap the Share button, then “Add to Home Screen”.
A new version is available
Reload to get the latest Vuci.