<!-- mobian-agent-page publisher="dailydev" canonical="https://daily.dev/posts/agentic-security-permissions-provenance-and-the-agent-supply-chain-steve-yegge-gas-town-wuj9pleh0" -->

---
title: Agentic Security: Permissions, Provenance, and the Agent...
description: Steve Yegge delivers a conference talk warning developers about the rapidly expanding security risks introduced by AI coding agents. Key concerns include:...
canonical: https://daily.dev/posts/agentic-security-permissions-provenance-and-the-agent-supply-chain-steve-yegge-gas-town-wuj9pleh0
twitter:card: summary_large_image
twitter:site: @dailydotdev
og:type: website
og:site_name: daily.dev
og:title: Agentic Security: Permissions, Provenance, and the Agent Supply Chain — Steve Yegge, Gas Town | daily.dev
og:description: Steve Yegge delivers a conference talk warning developers about the rapidly expanding security risks introduced by AI coding agents. Key concerns include:...
og:url: https://daily.dev/posts/agentic-security-permissions-provenance-and-the-agent-supply-chain-steve-yegge-gas-town-wuj9pleh0
og:image: https://api.daily.dev/og/posts/wuj9pLEh0.png
og:image:alt: Agentic Security: Permissions, Provenance, and the Agent Supply Chain — Steve Yegge, Gas Town
og:image:width: 1200
og:image:height: 630
og:locale: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Agentic Security: Permissions, Provenance, and the Agent Supply Chain — Steve Yegge, Gas Town

**[AI Engineer](https://daily.dev/sources/aidotengineer)** · 22 min read · 0 upvotes · 0 comments

## Summary

Steve Yegge delivers a conference talk warning developers about the rapidly expanding security risks introduced by AI coding agents. Key concerns include: AI-generated code increasing vulnerability surface area at 10x the rate, slop squatting (attackers uploading malicious packages matching AI-hallucinated package names), prompt injection attacks, and agents running with excessive permissions. He recommends treating security as a dedicated multi-pass review step separate from correctness, integrating tools like Snyk and Chainguard into LLM workflows, and designing adversarial agent oversight systems now before engineers spin up poorly-permissioned agents at scale. He also warns about AI-powered social engineering scams targeting individuals and families.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://www.youtube.com/watch?v=yWS0udrIOc8>

## Similar posts on daily.dev

- [Agentic AI Security: Defending Against Prompt Injection and Tool Misuse](https://daily.dev/posts/agentic-ai-security-defending-against-prompt-injection-and-tool-misuse-8x1r1ytqn) · Machine Learning Mastery · 1 upvotes · 0 comments
- [The New Security Risks of Agentic Development](https://daily.dev/posts/the-new-security-risks-of-agentic-development-rjskp1wg4) · Snyk · 1 upvotes · 0 comments
- [AI Agents 'Swarm,' Security Complexity Follows Suit](https://daily.dev/posts/ai-agents-swarm-security-complexity-follows-suit-4od27hgho) · Dark Reading · 3 upvotes · 0 comments

---

Tags: [#security](https://daily.dev/tags/security), [#ai-agents](https://daily.dev/tags/ai-agents), [#prompt-injection](https://daily.dev/tags/prompt-injection)

[View this post on daily.dev](https://daily.dev/posts/agentic-security-permissions-provenance-and-the-agent-supply-chain-steve-yegge-gas-town-wuj9pleh0)

```json
{"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]}
{"@context":"https://schema.org","@type":"TechArticle","headline":"Agentic Security: Permissions, Provenance, and the Agent Supply Chain — Steve Yegge, Gas Town","url":"https://daily.dev/posts/agentic-security-permissions-provenance-and-the-agent-supply-chain-steve-yegge-gas-town-wuj9pleh0","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/agentic-security-permissions-provenance-and-the-agent-supply-chain-steve-yegge-gas-town-wuj9pleh0"},"datePublished":"2026-07-20T17:41:33.372Z","dateModified":"2026-07-20T17:41:55.288Z","description":"Steve Yegge delivers a conference talk warning developers about the rapidly expanding security risks introduced by AI coding agents. Key concerns include:...","image":"https://i.ytimg.com/vi/yWS0udrIOc8/sddefault.jpg","thumbnailUrl":"https://i.ytimg.com/vi/yWS0udrIOc8/sddefault.jpg","isAccessibleForFree":true,"articleSection":"AI Engineer","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"AI Engineer","logo":"https://media.daily.dev/image/upload/s--u5PucxNT--/f_auto/v1724338940/logos/aidotengineer","url":"https://daily.dev/sources/aidotengineer"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/agentic-security-permissions-provenance-and-the-agent-supply-chain-steve-yegge-gas-town-wuj9pleh0","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"security,ai-agents,prompt-injection","timeRequired":"PT22M","video":{"@type":"VideoObject","name":"Agentic Security: Permissions, Provenance, and the Agent Supply Chain — Steve Yegge, Gas Town","description":"Steve Yegge delivers a conference talk warning developers about the rapidly expanding security risks introduced by AI coding agents. Key concerns include:...","thumbnailUrl":"https://i.ytimg.com/vi/yWS0udrIOc8/sddefault.jpg","uploadDate":"2026-07-20T17:41:33.372Z","duration":"PT22M","url":"https://api.daily.dev/r/wuj9pLEh0","embedUrl":"https://www.youtube.com/embed/yWS0udrIOc8"}}
{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"AI Engineer","item":"https://daily.dev/sources/aidotengineer"},{"@type":"ListItem","position":3,"name":"Agentic Security: Permissions, Provenance, and the Agent Supply Chain — Steve Yegge, Gas Town"}]}
```

