---
title: "Beyond source code: The files AI coding agents trust — and attackers exploit"
url: https://daily.dev/posts/beyond-source-code-the-files-ai-coding-agents-trust-and-attackers-exploit-pduvvginp
source_url: https://cloud.google.com/blog/products/identity-security/beyond-source-code-the-files-ai-coding-agents-trust-and-attackers-exploit
type: article
source: "Google Cloud"
published: 2026-05-12T16:05:05.600Z
updated: 2026-05-12T16:05:33.188Z
tags: ["security", "ai-agents", "prompt-injection"]
reading_time: 11
upvotes: 0
comments: 0
language: 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.

# Beyond source code: The files AI coding agents trust — and attackers exploit

**[Google Cloud](https://daily.dev/sources/gcp)** · 11 min read · 0 upvotes · 0 comments

## Summary

As AI coding agents become embedded in developer workflows, the attack surface has expanded well beyond source code to include configuration files, agent instruction files, runtime settings, and IDE extensions. Four attack surface categories are identified: what executes (project configs that trigger commands), what instructs (agent instruction files like CLAUDE.md or Skill.md that steer agent behavior), what connects (runtime configs that redirect API endpoints or expose external services), and what extends (IDE extensions with broad system access). Real-world examples from VirusTotal include a weaponized tasks.json linked to North Korean threat actors, Skill.md files instructing agents to exfiltrate API keys, settings.json files that silently redirect Claude Code traffic to third-party proxies, and a VS Code extension containing protestware. Traditional signature-based scanners miss these threats because the files are syntactically valid. Google recommends semantic analysis via VirusTotal Code Insight and agentic threat intelligence to detect malicious intent in plain-text artifacts, alongside repository-level security policies and least-privilege access for coding agents.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://cloud.google.com/blog/products/identity-security/beyond-source-code-the-files-ai-coding-agents-trust-and-attackers-exploit>

## Similar posts on daily.dev

- [Hackers are hiding malware behind AI agents that antivirus cannot see](https://daily.dev/posts/hackers-are-hiding-malware-behind-ai-agents-that-antivirus-cannot-see-5kzqds6hd) · TechCentral · 1 upvotes · 0 comments
- [Auditing Agent Skills: A Threat Model for the Next Generation of AI Package Managers](https://daily.dev/posts/auditing-agent-skills-a-threat-model-for-the-next-generation-of-ai-package-managers-vxdluywso) · DEV · 8 upvotes · 0 comments
- [The AI security gap nobody wants to admit is already here](https://daily.dev/posts/the-ai-security-gap-nobody-wants-to-admit-is-already-here-w12qpgipm) · The Next Web · 0 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/beyond-source-code-the-files-ai-coding-agents-trust-and-attackers-exploit-pduvvginp)