AI reverse engineering let researchers add a new feature to Slack

Intezer researchers used AI agents to rebuild source code for Slack, Apple’s Finder and a TinyTurla-NG sample, from a backdoor family Cisco Talos attributes to the Turla group.

They worked from the shipped programs and vendor documentation.

The rebuilt Slack ran well enough that the team added a new feature to it: AI text autocomplete, powered by a small local model.

Slack’s server is not downloadable, so the agents built a Slack-compatible one on SQLite, guided by network inspection of the real Slack app and Slack’s documentation.

Software vendors that count on compiling their programs to keep source code private are the ones exposed.

The same method that opens up a commercial app also opens up malware; the agents produced about 3,100 lines of source in two files.

Finder, a 25.8 MB executable, still has gaps around online-only files, sync status and actions that depend on other macOS services.

The same method that opens up a commercial app also opens up malware.

Codex, running GPT-5.6-sol-high, drove the workflow and made the engineering decisions, while Kimi K3 filled three separate roles in the setup.

The researchers say these “raise the bar” for AI agents.