MEDIUMAi
Global

'Ghostcommit' hides prompt injection in images to fool AI agents, steal secrets

·Source: BleepingComputer

Updated:

Executive Summary

A PNG hiding a prompt injection could steal your repo's secrets, researchers demonstrate. The technique, dubbed 'Ghostcommit,' slipped past AI code reviewers CodeRabbit and Bugbot, which never open image files at all, then convinced a coding agent to read a repo's .env and write every secret into the code as a list of numbers. [...]

Analysis

A PNG hiding a prompt injection could steal your repo's secrets, researchers demonstrate. The technique, dubbed 'Ghostcommit,' slipped past AI code reviewers CodeRabbit and Bugbot, which never open image files at all, then convinced a coding agent to read a repo's .env and write every secret into the code as a list of numbers. [...]
Source Attribution

Originally published by BleepingComputer on Jul 11, 2026.

Related Threats