microsoft / microsoft/semantic-kernel

[Feature Request]: Add Creduent zero-trust agent verification plugin to Semantic Kernel Python

Open
#14,248 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
C#
Stars
28.6k
Forks
4.8k
Avg merge
14h 13m
Merged PRs (30d)
18

Description


name: Feature request
about: Suggest an idea for this project


Feature Request Summary

Add native support for Creduent agent identity verification to Microsoft Semantic Kernel (semantic-kernel).

As autonomous agents delegate tasks to sub-agents and external plugins, zero-trust verification of target agent identity is critical to prevent untrusted execution loops and unverified prompt injections.

Creduent (creduent) is an open-source agent identification protocol that performs local cryptographic signature verification (Ed25519 + JCS RFC 8785) of agent URIs (agent://<namespace>/<name>) in under 5ms.

Proposed Solution

Introduce CreduentSemanticKernelPlugin to wrap and verify target agent attestations prior to Kernel invocation:

from creduent.semantickernel import CreduentSemanticKernelPlugin

plugin = CreduentSemanticKernelPlugin(
    agent_uri="agent://planner.dev/agent",
    timeout=10
)
kernel.add_plugin(plugin)
result = await kernel.invoke("PlanTask", {...})
Additional Context

I have the implementation and unit test suite ready to submit as a Pull Request.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with Semantic Kernel's Python plugin API and the proposed CreduentSemanticKernelPlugin entry point, then review the Creduent SDK and its Ed25519/JCS verification behavior. Done means target agent attestations are verified before Kernel invocation and the accompanying unit test suite covers the integration.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
ai, security
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Quiet
Clarity
Mostly clear
Newbie friendliness
48/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.