--- title: "From Indirect Prompt Injection to DNS Exfiltration in macOS Terminal · Embrace The Red" url: https://daily.dev/posts/from-indirect-prompt-injection-to-dns-exfiltration-in-macos-terminal-embrace-the-red-g5b1m75zv source_url: https://embracethered.com/blog/posts/2026/macos-terminal-dillma-dns-exfil-ansi-escape-code-fix type: article source: "Embrace The Red" published: 2026-07-17T01:23:53.728Z updated: 2026-07-17T06:21:26.444Z tags: ["security", "mac", "prompt-injection"] reading_time: 4 upvotes: 1 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. # From Indirect Prompt Injection to DNS Exfiltration in macOS Terminal · Embrace The Red **[Embrace The Red](https://daily.dev/sources/embracethered)** · 4 min read · 1 upvotes · 0 comments ## Summary A security researcher demonstrates an end-to-end attack chain on macOS Terminal where indirect prompt injection in a CSV file causes an LLM-integrated CLI tool to emit ANSI escape codes that trigger DNS requests, exfiltrating data to an attacker-controlled server. The vulnerability was reported to Apple in December 2024 and fixed in macOS Tahoe 26.1. The post also provides guidance for CLI developers on safely encoding control characters using caret notation to prevent terminal hijacking via LLM output. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Mozilla Shows the Danger of Indirect Prompt Injections in AI Coding Agents](https://daily.dev/posts/mozilla-shows-the-danger-of-indirect-prompt-injections-in-ai-coding-agents-nqhoyxkhl) · DevOps.com · 0 upvotes · 0 comments - [macOS.Gaslight \| Rust Backdoor Turns Prompt Injection on the Analyst, Not the Sandbox](https://daily.dev/posts/macos-gaslight-rust-backdoor-turns-prompt-injection-on-the-analyst-not-the-sandbox-nmqiw3t0x) · SentinelLABS · 0 upvotes · 0 comments - [Gaslight macOS Malware Uses Prompt Injection to Evade AI Security Analysis](https://daily.dev/posts/gaslight-macos-malware-uses-prompt-injection-to-evade-ai-security-analysis-efxclc4os) · Security Boulevard · 1 upvotes · 0 comments - [Security reserchers tricked Apple Intelligence into cursing](https://daily.dev/posts/security-reserchers-tricked-apple-intelligence-into-cursing-bj4vjxidi) · The Register · 0 upvotes · 0 comments - [MAD Bugs: Even "cat readme.txt" is not safe](https://daily.dev/posts/mad-bugs-even-cat-readme-txt-is-not-safe-yf8mujkpy) · Hacker News · 0 upvotes · 0 comments --- Tags: [#security](https://daily.dev/tags/security), [#mac](https://daily.dev/tags/mac), [#prompt-injection](https://daily.dev/tags/prompt-injection) [View this post on daily.dev](https://daily.dev/posts/from-indirect-prompt-injection-to-dns-exfiltration-in-macos-terminal-embrace-the-red-g5b1m75zv)