# Prompt Injection Is the Input Bug of the Agent Era

DevFeed: [Prompt Injection Is the Input Bug of the Agent Era](<https://devfeed.tech/articles/prompt-injection-is-the-input-bug-of-the-agent-era-28988.md>)

Original publisher: [Read original article](<https://codingwithroby.substack.com/p/prompt-injection-is-the-input-bug>)

Author: Eric Roby

Published: 2026-07-07T12:02:21Z

Content type: opinion

Language: en

Sources: [Eric Roby](<https://devfeed.tech/sources/eric-roby.md>)

Topics: [prompt injection](<https://devfeed.tech/topics/prompt-injection.md>), [Application Security](<https://devfeed.tech/topics/application-security.md>), [Security](<https://devfeed.tech/topics/security.md>), [SQL](<https://devfeed.tech/topics/sql.md>), [trust](<https://devfeed.tech/topics/trust.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [application-security](<https://devfeed.tech/tags/application-security.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llm-applications](<https://devfeed.tech/tags/llm-applications.md>), [prompt-injection](<https://devfeed.tech/tags/prompt-injection.md>), [security](<https://devfeed.tech/tags/security.md>), [sql](<https://devfeed.tech/tags/sql.md>), [trust](<https://devfeed.tech/tags/trust.md>)

## AI overview

The article compares prompt injection in AI agents with SQL injection. It argues that agents may interpret untrusted content from messages, documents, web pages, emails, RAG data, and tool responses as instructions because language models do not maintain a hard boundary between data and instructions. It frames prompt injection as an application security problem rather than merely a prompt-writing problem.

## Source excerpt

SQL injection taught us not to trust raw user input. Agents force the next lesson: don't trust text just because the model can read it.