# Treating Issue Bodies as Untrusted Input

DevFeed: [Treating Issue Bodies as Untrusted Input](<https://devfeed.tech/articles/treating-issue-bodies-as-untrusted-input-34113.md>)

Original publisher: [Read original article](<https://philipptheserver.com/posts/prompt-injection-untrusted-issues/>)

Author: Philipp Lehmann (philipp.lehmann@gruppe.ai)

Published: 2026-08-14T07:00:00Z

Content type: tutorial

Language: en

Sources: [Philipp Lehmann](<https://devfeed.tech/sources/philipp-lehmann.md>)

Topics: [prompt injection](<https://devfeed.tech/topics/prompt-injection.md>), [GitHub](<https://devfeed.tech/topics/github.md>), [JSON Feed](<https://devfeed.tech/topics/json-feed.md>), [Structured-data](<https://devfeed.tech/topics/structured-data.md>), [issue tracker](<https://devfeed.tech/topics/issue-tracker.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [github](<https://devfeed.tech/tags/github.md>), [implementation](<https://devfeed.tech/tags/implementation.md>), [issue-tracker](<https://devfeed.tech/tags/issue-tracker.md>), [json](<https://devfeed.tech/tags/json.md>), [llm](<https://devfeed.tech/tags/llm.md>), [prompt-injection](<https://devfeed.tech/tags/prompt-injection.md>), [schema](<https://devfeed.tech/tags/schema.md>), [security](<https://devfeed.tech/tags/security.md>), [test](<https://devfeed.tech/tags/test.md>)

## AI overview

The article explains how GitHub issue bodies can carry prompt injection attacks when an agent treats public input as instructions. It recommends fencing untrusted text, clearly labeling it, constraining model output to a fixed JSON action schema, and testing the validation boundary without a live model.

## Source excerpt

Prompt injection via GitHub issue bodies: fence untrusted text and accept model output only as a fixed JSON action schema, tested without a model.