PrivacySignal
← Front page
News

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

BleepingComputer · · International · AI Governance

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. [...]

Who should care: General readers · AI governance · Policy

#ai
Read the original at BleepingComputer → Browse the archive

This summary is AI-assisted and may contain errors. It is an original briefing to help you gauge significance quickly — not a reproduction of the source. Always read the linked original before relying on it. See our methodology.

Related stories

News
The Guardian — Tech · · International

Meta ditches Muse Image AI feature because it ‘misses the mark’ on users’ privacy

Meta was criticised for feature launched on Tuesday that automatically lets users generate images using content from public Instagram accounts Meta has said ⁠it is discontinuing an AI feature launched this week that allowed users to generate images using public Instagram ⁠accounts, after drawing widespread ⁠criticism over ​privacy concerns, including from a Hollywood union. “Our intent was to provide a useful creative tool and to give people control ⁠over whether their public content could be referenced in this way,” Meta said in a statement. Continue reading...

Who should care: General readers · AI governance · Policy

#ai Read original →
AI Governance
N News From The States · · International

Young lawmakers talk online child safety and AI policy at annual bipartisan summit

A bipartisan group of young lawmakers gathered at an annual summit to discuss online child safety and AI policy. The meeting brought together legislators across party lines to exchange views on two of the most contested areas of digital regulation.

Who should care: AI governance · Lawyers · Administrators · General readers · Policy

#ai-governance#ai Read original →
AI Governance
W WSJ · · International

Opinion | Is Private AI Regulation Constitutional?

A Wall Street Journal opinion piece examines whether government regulation of private AI systems can withstand constitutional scrutiny, engaging the legal debate over how far lawmakers can go in controlling how private companies develop and deploy artificial intelligence.

Who should care: AI governance · Lawyers · Administrators · Compliance · General readers · Policy

#ai-governance#regulation#ai Read original →