# Before the first prompt: Code execution paths in trusted coding-agent projects

DevFeed: [Before the first prompt: Code execution paths in trusted coding-agent projects](<https://devfeed.tech/articles/before-the-first-prompt-code-execution-paths-in-trusted-coding-agent-projects-8281.md>)

Original publisher: [Read original article](<https://securitylabs.datadoghq.com/articles/coding-agent-project-trust-code-execution-before-first-prompt/>)

Author: Nick Frichette

Published: 2026-08-03T00:00:00Z

Content type: article

Language: en

Sources: [Datadog Security Labs](<https://devfeed.tech/sources/datadog-security-labs.md>)

Topics: [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [codex](<https://devfeed.tech/topics/codex.md>), [Model Context Protocol (MCP)](<https://devfeed.tech/topics/model-context-protocol-mcp.md>), [Social engineering](<https://devfeed.tech/topics/social-engineering.md>), [Visual Studio Code](<https://devfeed.tech/topics/visual-studio-code.md>), [npm packages](<https://devfeed.tech/topics/npm-packages.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [attacks](<https://devfeed.tech/tags/attacks.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [code](<https://devfeed.tech/tags/code.md>), [codex](<https://devfeed.tech/tags/codex.md>), [debugging](<https://devfeed.tech/tags/debugging.md>), [developers](<https://devfeed.tech/tags/developers.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [npm-packages](<https://devfeed.tech/tags/npm-packages.md>), [social-engineering](<https://devfeed.tech/tags/social-engineering.md>)

## AI overview

This security article examines how trusted coding-agent projects can execute repository-controlled code before a user sends the first prompt. It describes execution paths involving project-scoped MCP configuration in Codex and project-controlled environment settings and Git probes in Claude Code, without requiring a model response or shell-command approval.

## Source excerpt

Learn how trusted coding-agent projects can execute repository-controlled code before the first prompt through Codex MCP configuration and Claude Code environment settings.