Tuesday, August 11, 2026
LIVEThe Unrelenting Cyber Battle: Hacking Threats and the Imperative of Robust Data Protection///Navigating the Cyber Labyrinth: Bolstering Defenses Against Evolving Hacking Threats///The Dual Front War: Battling Hacking and Bolstering Data Protection in the Digital Age///The Ever-Evolving Cyber Threat Landscape: Navigating Hacking and Fortifying Data Protection///The Unseen Battle: Fortifying Data in an Age of Relentless Hacking///The Unseen War: Hacking's Relentless Advance and the Imperative of Data Protection///The Evolving Threat Landscape: Hacking, Data Protection, and the Imperative for Proactive Security///Navigating the Digital Minefield: Bolstering Data Protection in an Era of Relentless Hacking///The Dual Fronts of Digital Defense: Combating Hacking and Fortifying Data Protection///Hacking's New Frontier: Fortifying Data Protection in the Age of Advanced Cyber Threats///The Dual Front: Navigating Hacking Threats and Fortifying Data Protection in the Digital Age///Navigating the Digital Gauntlet: The Evolving Nexus of Hacking and Data Protection///The Unrelenting Cyber Battle: Hacking Threats and the Imperative of Robust Data Protection///Navigating the Cyber Labyrinth: Bolstering Defenses Against Evolving Hacking Threats///The Dual Front War: Battling Hacking and Bolstering Data Protection in the Digital Age///The Ever-Evolving Cyber Threat Landscape: Navigating Hacking and Fortifying Data Protection///The Unseen Battle: Fortifying Data in an Age of Relentless Hacking///The Unseen War: Hacking's Relentless Advance and the Imperative of Data Protection///The Evolving Threat Landscape: Hacking, Data Protection, and the Imperative for Proactive Security///Navigating the Digital Minefield: Bolstering Data Protection in an Era of Relentless Hacking///The Dual Fronts of Digital Defense: Combating Hacking and Fortifying Data Protection///Hacking's New Frontier: Fortifying Data Protection in the Age of Advanced Cyber Threats///The Dual Front: Navigating Hacking Threats and Fortifying Data Protection in the Digital Age///Navigating the Digital Gauntlet: The Evolving Nexus of Hacking and Data Protection///
Subscribe
Cyber Security
Independent · Digital
Thehackingpost
RSSSubscribe
CybersecurityAI-assisted

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

A security vulnerability identified as "PromptPwnd" affects AI agents integrated into GitHub Actions and GitLab CI/CD pipelines. This vulnerability enables attackers to inject malicious prompts through untrusted user inputs, such as issue titles or pull…

ABy Aiden SinclairDec 06, 20251 min read

A security vulnerability identified as "PromptPwnd" affects AI agents integrated into GitHub Actions and GitLab CI/CD pipelines. This vulnerability enables attackers to inject malicious prompts through untrusted user inputs, such as issue titles or pull request bodies, potentially causing AI models to execute unauthorized commands that could leak secrets or alter workflows.

Several Fortune 500 companies are potentially exposed to this vulnerability, including Google's Gemini CLI repository, which was quickly patched in response to this discovery.

The vulnerability arises when repositories integrate raw user content, such as ${{ github.event.issue.body }} , directly into AI prompts for tasks such as issue triage or PR labeling. Agents like Gemini CLI, Anthropic’s Claude Code, OpenAI Codex, and GitHub AI Inference process these inputs alongside high-privilege tools, including commands that access sensitive tokens and API keys.

In a proof-of-concept, researchers demonstrated the vulnerability by submitting an issue with hidden instructions that prompted the AI model to expose sensitive tokens publicly. Google addressed this issue within four days of disclosure through its OSS Vulnerability Rewards Program.

A security vulnerability identified as "PromptPwnd" affects AI agents integrated into GitHub Actions and GitLab CI/CD pipelines.
Aiden Sinclair · Thehackingpost

This incident represents the first confirmed instance of prompt injection attacks compromising CI/CD pipelines. The attack surface is expanded in certain workflows that allow activation on any user's issue submission, thus increasing the risk from external threats.

To mitigate such risks, the following strategies are recommended:

Restrict AI toolsets to prevent unauthorized issue edits or shell access. Sanitize user inputs before processing them with AI tools. Validate all AI outputs as potentially untrusted code. Limit token scopes by IP using GitHub's security features.

Advertisement

Configurations that allow broad user access, such as Claude’s allowed_non_write_users: "" or Codex’s allow-users: "" , should be reviewed to reduce associated risks.

As AI continues to automate development workflows, the PromptPwnd vulnerability highlights the importance of auditing AI integrations to prevent unauthorized access to sensitive information.

Based on reporting by Cyber Security News.

AI transparency. This article was produced with the assistance of artificial intelligence and published under human editorial oversight. AI systems can make mistakes. Read how we use AI (EU AI Act, Art. 50).
Related Stories
Cybersecurity

Why Fintech Banking Platforms Are Reducing Operational Costs by 40%

Paige Monroe · Mar 26, 2026
Cybersecurity

Dogecoin Price Prediction: SHIB Burns 172M Tokens as Pepeto Exchange Earns From Every Trade

Eric Wallace · Mar 26, 2026
Cybersecurity

Solana Price Prediction: SOL Holds $86 With Commodity Status as Pepeto Targets Bigger Returns

Zachary Burns · Mar 26, 2026
Cybersecurity

Open Directory Malware Campaign Uses Obfuscated VBS, PNG Loaders and RAT Payloads

Joseph Cain · Mar 26, 2026