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

Prompt Injection Flaw in GitHub Actions Hits Fortune 500 Firms

Recent research by Aikido Security has identified a new class of vulnerabilities called "PromptPwnd" affecting GitHub Actions and GitLab CI/CD pipelines integrated with AI agents. These vulnerabilities have been confirmed to impact multiple Fortune 500…

ZBy Zachary BurnsDec 05, 20251 min read

Recent research by Aikido Security has identified a new class of vulnerabilities called "PromptPwnd" affecting GitHub Actions and GitLab CI/CD pipelines integrated with AI agents. These vulnerabilities have been confirmed to impact multiple Fortune 500 companies and are believed to be widespread.

The vulnerabilities involve untrusted user input being injected into AI prompts, enabling the AI agents to execute unauthorized commands. This can result in the exposure of sensitive information or the manipulation of workflows. Aikido Security has released open-source Opengrep rules to assist security vendors in detecting these vulnerabilities.

The issue arises when untrusted content from sources such as GitHub issue titles is used directly in AI prompts. Malicious instructions can be embedded within this content, leading the AI model to execute these as commands rather than interpreting them as data. This can lead to unauthorized actions, such as editing pull requests or leaking sensitive credentials.

These vulnerabilities have been confirmed to impact multiple Fortune 500 companies and are believed to be widespread.
Zachary Burns · Thehackingpost

An example of this vulnerability was found in Google's Gemini CLI repository. Aikido Security demonstrated a proof-of-concept by submitting a malicious issue with hidden instructions, which the AI agent executed, leading to the exposure of sensitive API keys. Following responsible disclosure, Google addressed the vulnerability within four days.

Restrict the toolset available to AI agents, avoiding tools that can write to issues or pull requests. Avoid injecting untrusted user input into AI prompts, or sanitize and validate it if unavoidable. Treat all AI-generated output as untrusted code and validate it before execution. Limit GitHub token access by IP address to mitigate potential damage from credential leaks.

Advertisement

Aikido Security provides a free tool to scan GitHub and GitLab repositories for these vulnerabilities. Additionally, developers can use open-source tools to check their .yml files.

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