---
title: "We Vetted 2,000 AI Skills Before They Reached Developers"
category: "talks"
date: "2026-07-01"
time: "1:55pm-2:15pm"
track: "AI in Finance"
room: "Track 3"
speakers: ["Lucas Palma"]
sourceLabels: ["Official conference schedule", "Public YouTube metadata"]
scheduleTrack: "AI in Finance"
scheduleRoom: "Track 3"
scheduleLabels: ["AI in Finance", "Track 3", "session", "confirmed"]
---
# We Vetted 2,000 AI Skills Before They Reached Developers

## Conference Context
- Date/time: 2026-07-01 · 1:55pm-2:15pm
- Track/room: AI in Finance · Track 3
- Speaker(s): Lucas Palma
- Session type/status: session · confirmed

- Track: AI in Finance
- Room: Track 3
- Session type: session
- Status: confirmed

## Session Description
AI skills and plugins are becoming part of the software supply chain. They steer agent behavior, describe tools, run commands, access files, and shape how developers build with AI. Treating them as harmless configuration is a mistake. This talk shares what we learned from building an automated security review system for more than 2,000 internal AI skills before they reached a company wide plugin marketplace. I will walk through the risks we found, the checks that worked, the checks that created noise, and how we turned skill review into something developers could run locally and in CI. We will cover practical patterns for reviewing unsafe instructions, destructive commands, sensitive data exposure, risky tool use, credential handling, external calls, and agent behavior drift. The goal is to help AI engineers think about skills, plugins, and agent instructions as production dependencies that deserve review before they reach real users.

## Media Evidence
No related AI Engineer channel video found yet.

## Evidence Graph
This evidence graph is generated from currently linked source material: official schedule text, related video pages, cached transcripts, visible slide text, dense/reconstructed slide pages, and AI slide-classification audits.

### Media Signals
No linked video, transcript, or slide source has been attached yet.

### Agent Reading Notes
Use these signals to refine the synopsis, topic links, people/company context, and method notes. If a source is a related external video rather than an exact official recording, keep it framed as supporting evidence.

## Transcript Status
No official session recording transcript was found by exact title match on the AI Engineer YouTube channel during this run.

## People
- [[lucas-palma]]

## Notes
- Pending transcript synthesis when an official recording or confirmed matching video is available.

## Synthesis
### Synthesized Breakdown
# We Vetted 2,000 AI Skills Before They Reached Developers ## Conference Context - Date/time: 2026-07-01 · 1:55pm-2:15pm - Track/room: AI in Finance · Track 3 - Speaker(s): Lucas Palma - Session type/status: session · confirmed - Track: AI in Finance - Room: Track 3 - Session type: session - Status: confirmed ## Session Description AI skills and plugins are becoming part of the software supply chain. They steer agent behavior, describe tools, run commands, access files, and shape how developers build with AI. Treating them as harmless configuration is a mistake. This talk shares what we learned from building an automated security review system for more than 2,000 internal AI skills before they reached a company wide plugin marketplace.

### Speaker And Company Context
- [[lucas-palma|Lucas Palma]] — Information Security Manager at [[nubank|Nubank]].

### Topics Covered
- [[agent-security]]
- [[coding-agents]]

### Derived Links And Source Material

### Novel Concepts / Clever Methods
- No highlighted novel concept has been detected yet.

### Evidence Boundary
This synthesis is based on the official schedule and linked source pages. It should be revisited when exact session recordings or transcript-backed secondary sources are available.