docs: lead Impart Security plugin page with AI (LLM/agent/MCP) protection#5889
Draft
brianwjoe wants to merge 4 commits into
Draft
docs: lead Impart Security plugin page with AI (LLM/agent/MCP) protection#5889brianwjoe wants to merge 4 commits into
brianwjoe wants to merge 4 commits into
Conversation
…tion Rewrites the Impart Security plugin doc to match current Impart positioning (runtime enforcement, block-not-alert) and lead with LLM, agent, and MCP protection ahead of API/web app coverage, per Kong's partner plugin doc template (introduction, how it works, installation details). Adds a request-flow sequence diagram and expands tags/search_aliases so the page surfaces for AI-related searches alongside its existing WAF/API matches.
👷 Deploy request for kongdeveloper pending review.Visit the deploys page to approve it
|
|
|
Per Kong reviewer feedback on PR Kong#5889, narrows the page to lead exclusively with LLM/agent/MCP protection (dropping API/web app as a co-equal bullet), modeled on the Prisma AIRS Intercept page's AI-use-case framing. Adds explicit pointers to Impart's own Kong integration documentation for deeper technical/architecture detail, and moves broader API/web coverage to a single supporting note rather than a headline claim.
Author
|
updated |
Removed the section on enabling the Impart plugin and its requirements.
Drop 'sensitive data exposure' from the blocked-attacks bullet — the plugin only blocks on the request side; response inspection is detect-only and can't prevent a leaked-data response from reaching the client.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
app/_kong_plugins/impart/index.md) to reflect Impart's current product positioning: a unified runtime enforcement platform that blocks LLM, agent, and MCP attacks inline, with API/web app protection as the underlying foundation rather than the headline.ai-sanitizer,ai-prompt-compressor,crowdstrike-aidr-request).aitotagsand expandssearch_aliases(llm security, ai security, agent security, mcp security, prompt injection, runtime protection) so the page surfaces for AI-related searches, in addition to the existing WAF/API matches it already gets via its description text.schema.json,examples/enable-impart.yaml, or the plugin icon — existing collateral is accurate and unchanged.Test plan
install-third-party.md), and the Mermaid sequence diagram all render correctly{{page.name}}and{{site.base_gateway}}template variables resolve as expectedsecurity+ai)