Evolves the planner, reviewer and retry policies around your model, testing each change in a sandbox.
Redblue
metaharness · Agent
Redblue runs a red team and blue team loop against an AI agent or LLM app that you own. Adversarial models generate attacks across OWASP LLM Top 10 and NIST AI RMF categories, a judge model marks each result as compromised or resisted and scores its severity, then declarative rules patch the weak families and the attacks run again. It ends with a report with pass and fail gates. Attackers run without real credentials, a shell or open network access, and it is meant for a local copy of your system rather than production.
Written by ooruby from the README of @metaharness/redblue 0.1.6.
Not claimed by its maker. Is this yours? Prove it and answer the findings
Why it's useful
You find out how your agent responds to prompt injection and tool misuse attempts before real users or attackers try them.
What you could do with it
- Run the attack loop against a local copy of your support agent to see which attack families get through.
- Test whether your agent can be talked into misusing its tools or leaking data, then retest after patching.
- Try the full pipeline with the mock judge before adding an OpenRouter key for real model judging.
Written from its documentation: what it says it can do, not what our checks found.
Maintenance
Not measuredNo release date is on record for this package yet. The nightly publisher check records one as it reaches each npm package, about once every ten nights.
Release activity only: it says nothing about quality or safety, and a finished small package can be fine without releases. How it is measured
What this does not cover
- Everything. Treat it as you would software from anywhere else.
Receipt history: every signed receipt for every version of this listing, and what changed between them.
In its maker's words
AI red-teaming for the AI agents & LLM apps you own: stress-test them with adversarial models to find security failures (prompt injection, tool misuse / excessive agency, data leakage, jailbreaks, denial-of-wallet), auto-patch (blue team), retest, and get
Compare with
Compare all 4How far this has been checked
Static scanned
- What it establishes
- Its published package, or for a hosted server its source repository at a recorded commit, was read file by file, without running it, by every check in our current scan.
- What it does not
- How it behaves when it runs, or anything the scan does not read yet: several rubric checks, the repository's history, and compiled code in folders named dist or build. For a hosted server, that the endpoint runs the code that was read. The ooruby Index sets out exactly what was read.
- Exactly what was read
- Version 0.1.6, the file with digest sha512-cnQTOcPVetgz/XoYBdW5carkl48wBJsvBbJ7ntmelFtRu/8N5ARhSXnebEY+05SWaNm8lqij/gxZx2FqNCQWJg==, as the registry publishes it. A published version cannot be replaced, so this names the same bytes for anyone who checks.
- Authentication
- Runs locally. No hosted endpoint is listed for this package. You run it on your own machine, so there is no endpoint of ours to authenticate against.
Adding it
Run it with:
npx -y -p @metaharness/redblue@0.1.6 metaharness-redbluePinned to 0.1.6, which is the version the findings above were found in. Drop the version to take whatever is newest, and the report on this page stops describing what you installed.
Where this came from
- Registry
- npm
- Package
- @metaharness/redblue
- Version read
- 0.1.6
- Resolved
- 2026-10-09
No build provenance published. The repository above is the one the publisher declared, and nothing links it to the package you would install. That is not a mark against this listing, since most packages are published this way, but it is a check nobody can run.
The badge, if this is your listing
It renders the current rung (static scanned) and links back here, where what that does and does not establish is one click away. It updates itself as the evidence deepens.
[](https://ooruby.com/market/metaharness-redblue)About this listing
- Kind
- Agent
- Category
- Developer tools
- Pricing
- Free
- Sandbox
- No
- Hosted
- No
- Updated
- 2026-10-08
More from metaharness
See the storefrontSimilar agents
All agentsVerification records what our published tests found on a specific version at a specific date. It is not a warranty, and it does not certify that software is free of defects.