Announcing CISCO Foundry Security Spec

Cisco announced the open-source Foundry Security Spec, a battle-tested blueprint for building an agentic security evaluation system. The specification is model-agnostic and stack-agnostic, designed to help organizations shift from noisy, hallucinated alerts to verifiable security findings. Foundry is published as two main artifacts: the "spec" (eight core agent roles, five extension roles, a finding lifecycle, a coordination substrate, and roughly 130 functional requirements with rationale) and the "constitution" (eleven inviolable principles each based on real production failures). The system wraps frontier LLMs in orchestration, roles, and guardrails to produce bounded, prioritized, verifiable findings with a clear "done" signal and auditable provenance. Foundry is meant to be used with GitHub's spec-kit and pairs with Cisco's previously open-sourced Project CodeGuard (donated to CoSAI) to create a self-improving flywheel: CodeGuard rules provide systematic detection, Foundry's exploratory agents find novel issues, gaps become new CodeGuard rules, and those rules then prevent bugs at development time. The specification is a seed and blueprint, not a turnkey scanner, and is available at `https://github.com/CiscoDevNet/foundry`. 

https://blogs.cisco.com/ai/announcing-foundry-security-spec

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

SecObserve: Simplified Vulnerability and License Management for CI/CD Pipelines

 SecObserve is an open-source tool for managing vulnerabilities and licenses in software development and cloud environments. It integrates various vulnerability scanners into CI/CD pipelines using GitLab CI templates and GitHub Actions for streamlined setup. It offers a centralized dashboard for assessing and reporting vulnerabilities, with tools for filtering, sorting, and evaluating results. SecObserve supports automation and manual assessments to focus on resolving critical issues.  https://github.com/MaibornWolff/SecObserve/tree/dev
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