hackerbot-claw: An AI-Powered Bot Actively Exploiting GitHub Actions

This blog post from StepSecurity details a week-long automated attack campaign in February and March 2026 where an autonomous AI bot called hackerbot-claw systematically exploited GitHub Actions workflows across major open source repositories, including those belonging to Microsoft, DataDog, CNCF, and popular projects like Trivy and awesome-go. The bot used five different exploitation techniques including poisoned Go scripts via pull_request_target workflows, direct script injection, branch name injection, filename injection with base64 encoded commands, and AI prompt injection targeting Claude Code reviewers through poisoned configuration files. In the most severe incident, the attacker stole a personal access token from the aquasecurity/trivy repository and achieved full repository takeover, making the repository private, deleting years of releases, and pushing a malicious artifact to the Open VSX marketplace. The campaign successfully compromised at least five of seven targeted repositories, with only Claude’s built-in prompt injection detection stopping the AI-targeted attack. The post emphasizes that autonomous attacks require automated defenses and recommends implementing network egress monitoring, minimum token permissions, static workflow analysis, and developer MDM solutions to prevent similar compromises. 

https://www.stepsecurity.io/blog/hackerbot-claw-github-actions-exploitation

Comments

Post a Comment

Popular posts from this blog

Prompt Engineering Demands Rigorous Evaluation

In the blog post “Prompt Engineering Requires Evaluation” on the Shostack + Associates website, the author argues that treating prompts for large language models (LLMs) merely as creative artefacts is insufficient. Engineering prompts properly demands structured evaluation frameworks — what the AI community calls “evals” — to test which prompt versions work better, with which models, and under which conditions. The post highlights that simply assuming a prompt is “good enough” creates risks when LLMs are integrated into production systems (e.g., for threat modeling). It advocates for measuring prompt performance, variation effects, and tool-chain dependencies (model, context, ancillary materials).  Ultimately the message is: prompt engineering should borrow disciplined practices from software engineering (versioning, testing, benchmarking) rather than relying on informal experimentation.  https://shostack.org/blog/prompt-enignieering-requires-evaluation/
Read more

Secure Vibe Coding Guide: Best Practices for Writing Secure Code

Ken Huang's "Secure Vibe Coding Guide" emphasizes the importance of integrating security into the software development lifecycle. The guide provides best practices for writing secure code, including input validation, proper authentication mechanisms, and secure data storage techniques. It also highlights the necessity of regular code reviews and staying updated with the latest security vulnerabilities and patches. By following these guidelines, developers can create applications that are resilient against common security threats and contribute to a safer digital environment.  https://kenhuangus.substack.com/p/secure-vibe-coding-guide
Read more

KEVIntel: Real-Time Intelligence on Exploited Vulnerabilities

KEVIntel is a dynamic platform providing up-to-date information on known exploited vulnerabilities (KEVs). It aggregates data from over 50 public sources, including CISA, and enriches each entry with metadata such as EPSS scores, online mentions, scanner inclusion, and exploitation status. The platform aims to serve as an early warning system, offering insights even before official publications. KEVIntel supports various formats like JSON, CSV, and RSS, facilitating integration into security operations. These entries include CVSS scores, exploit status, and links to proof-of-concept code, aiding organizations in prioritizing remediation efforts.   https://kevintel.com/
Read more