Researchers Hack Google’s Gemini CLI Through Prompt Injections in GitHub Actions

Cybersecuritynews •Guru Baran • December 6, 2025

A critical vulnerability class dubbed “PromptPwnd,” affects AI agents integrated into GitHub Actions and GitLab CI/CD pipelines. This flaw allows attackers to inject malicious prompts via untrusted user inputs like issue titles or pull request bodies, tricking AI models into executing privileged commands that leak secrets or alter workflows. At least five Fortune 500 companies […]

The full story

This article is one source in a clustered incident — the cluster page carries the summary, timeline and every other outlet covering it.

Critical Prompt Injection Vulnerability Affects AI in CI/CD Pipelines Researchers have identified a critical vulnerability class named 'PromptPwnd' that affects AI agents in GitHub Actions and GitLab CI/CD pipelines. This vulnerability allows attackers to inject malicious prompts through untrusted user inputs, leading to the execution of privileged commands that can leak sensitive information. At least five Fortune 500 companies, including Google, have been impacted by this flaw. 3 sources 20

Extracted Entities

Researchers Hack Google’s Gemini CLI Through Prompt Injections in GitHub Actions

The full story

Extracted Entities

Attack Types (1)

Campaigns (1)

Platforms (1)

Tools (1)