ClawGuard: AI Agent Security Scanner

ClawGuard is an open-source security scanner that acts as a firewall for AI agents, detecting prompt injection, jailbreaks, and data exfiltration in real time. It features 216 detection patterns across 13 categories, supports 15 languages, and achieves sub-10 millisecond scan times with an F1 score of 99 percent using pure Python with no external dependencies or API calls. The scanner includes a 10-stage preprocessing pipeline to catch evasion techniques like leetspeak, zero-width characters, homoglyphs, and base64 encoding, along with confidence scoring for each finding. ClawGuard offers a dedicated MCP security scanner for identifying hidden prompt injections in MCP server tool descriptions, an evaluation framework with 262 test cases, CLI and SARIF output for CI/CD integration, and compliance support for EU AI Act articles. The project has been used to responsibly disclose vulnerabilities in over 30 popular MCP servers and AI tools representing more than 280,000 combined GitHub stars, and is released under the MIT License. 

https://github.com/joergmichno/clawguard

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