ws4-secure-design-agentic-systems
Repository for CoSAI Workstream 4, Secure Design Patterns for Agentic Systems
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Check it deeper on your machine
It has changed since its scan on 11 Nov 2026.
As a Claude Code plugin, install it and then ask Claude Code:
/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/cosai-oasis/ws4-secure-design-agentic-systems with scanskillsafety
Or from a terminal, clone it and run it:
git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/cosai-oasis/ws4-secure-design-agentic-systems'
It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.
Badge for your README
Markdown
[](/listings/cosai-oasis--ws4-secure-design-agentic-systems)HTML
<a href="/listings/cosai-oasis--ws4-secure-design-agentic-systems"><img src="/api/listings/cosai-oasis--ws4-secure-design-agentic-systems/badge.svg" alt="findsafeskills safety rating" /></a>Install
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
README.md · README · 68 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
- <img src="https://github.com/cosai-oasis/oasis-open-project/blob/main/artwork/cosai-logo.png" width="150">
- <!--[**Note:** This template is provided to give you a good idea about the kind of information you should include in a README.md file as a best practice. You know your project inside-out. Write your readme file for someone who doesn't know anything about it. What do you want people to know about your project who are just coming across it for the first time? OASIS Staff are happy to collaborate with you as well.
- Further README inspiration can be found [here](https://www.makeareadme.com/) and [here](https://github.com/hackergrrl/art-of-readme#readme).
- You may copy and edit this template as you see fit for your project and your community. You are also welcome to use emojis, graphics or images in your README. This file should be reviewed regularly and kept up-to-date.]-->
- ## CoSAI Workstream 4: Secure Design Patterns for Agentic Systems
- This repository is for the work of the CoSAI Workstream 4, Secure Design Patterns for Agentic Systems. CoSAI is an [OASIS Open Project](https://www.oasis-open.org/open-projects/) and an open ecosystem of AI and security experts from industry leading organizations dedicated to sharing best practices for secure AI deployment and collaborating on AI security research and product development. For more information on CoSAI, please visit the [CoSAI website](https://www.coalitionforsecureai.org/) and the [Open Project repository](https://github.com/cosai-oasis/oasis-open-project) which has information regarding the governance, sponsors and rosters and the project charter.
- ### About this workstream
- The goal of this workstream is to research and develop secure design patterns for AI-based agentic systems including updates to AI usage threat models, conceptual high-level secure design pattern(s), impacts to secure infrastructure design, and other agent integration and use based needs. Further information can be found [here](https://github.com/cosai-oasis/oasis-open-project/blob/main/WORKSTREAMS.md).
- ### Workstream Leads
- * Ian Molloy (IBM)
- * Sarah Novotny
- #### Supporting Leads
- * Raghuram Yeluri (Intel)
- ### Published work from this workstream
- #### RFCs
- Active and approved RFCs:
- - [6. Model Context Protocol (MCP) Security Best Practices Gap Analysis](RFCs/RFC-6.md)
- - [50. Trust-Aware Dataplane for Agentic Systems](RFCs/RFC-50.md)
- #### Whitepapers
- This workstream has published and released the following whitepapers.
- - [Model Context Protocol (MCP) Security](whitepapers/model-context-protocol-security.md) and [PDF](whitepapers/model-context-protocol-security.pdf)
- - [Agentic Identity and Access Management](whitepapers/agentic-identity-and-access-control.md) and [PDF](whitepapers/agentic-identity-and-access-control.pdf)
- #### Runbooks
- Runbooks are practical guides, or "cookbooks" providing concrete examples, code snippets, Notebooks, and instantiations of the recommendations, best practices, and security requirements identified in the RFCs and Whitepapers. They are not intended as full solutions, but rather provide an illustration of how to turn the theory into practice.
- 1. [Tool Design for Secure Agentic Systems](practical-guides/mcp-secure-tool-design.md)
- 1. [Input and Data Sanitization and Filtering](practical-guides/input-and-data-sanitization-and-filtering.md)
- 1. [MCP Runtime Isolation](practical-guides/mcp-runtime-isolation.md)
- ## Contributing
- Check out our [onboarding guidance for new participants](https://github.com/cosai-oasis/oasis-open-project/blob/main/ONBOARDING.md) and please see the [CoSAI Contributing policy](CONTRIBUTING.md) for more details.
- <!-- Give a brief explanation of what kind of contributions you are looking for and what your requirements are for accepting them. Then link to
- [CONTRIBUTING.md](link to your contributing.md file) for more information and also add a link to [CODE_OF_CONDUCT](link to your code_of_conduct.md file).
- ## Authors and Maintainers - TBD
- Adds names / GitHub profile links for those who have contributed to this repository. If you have a maintainer's list, link to it here.-->
- ## Support
- For issues or features, please use Github issues. You can also join the workstream mailing list by posting an empty email to [cosai-agentic-systems-ws@lists.oasis-open-projects.org](mailto:cosai-agentic-systems-ws@lists.oasis-open-projects.org). You can read the mailing list archive [here](https://lists.oasis-open-projects.org/g/cosai-agentic-systems-ws/topics).
- You can also join us on Slack via [this link](https://join.slack.com/t/cosai-op/shared_invite/zt-2rbgqtolg-GdajCyOiddYtGJ3cSdk1Jg) and introduce yourself in the [#ws4-secure-design-agentic-systems](https://cosai-op.slack.com/archives/C08ET0T8L57) channel.
- ## Governance and Licenses
- CoSAI and the CoSAI workstream operates under the terms of the [Open Project Rules](https://www.oasis-open.org/policies-guidelines/open-projects-process), the [CoSAI Governance](https://github.com/cosai-oasis/oasis-open-project/blob/main/GOVERNANCE.md) and [Workstream Governance](https://github.com/cosai-oasis/oasis-open-project/blob/main/TSC-WS-GOVERNANCE.md), as well as the following the licenses:
- * CC-BY 4.0 for documentation and data contributions; and
- * Apache License v2.0 for source code and models
- The applicable license will be determined for each repository, as applicable, at the time of its
- creation.
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.