- Home
- AI Red Teaming Tools
- RedHub Prompt Injection Red Team Kit
On the recordRead 7 Oct 202614 facts
RedHub Prompt Injection Red Team Kit
Ormond Beach, Florida, USA
Plans and prices
Prompt Injection Red Team Kit
$99one-time
15 OWASP-mapped probes · Python + TypeScript · instant download · offline
Read 7 Oct 2026 · redhub.ai
On the record
- Authorized use
- The maker says to run the defensive kit only against systems you own or are explicitly authorized to test.redhub.ai · read 7 Oct 2026
- CI gate
- The kit provides tunable severity-weighted thresholds, ship/hold/fix verdicts, exit codes 0/1/2, and a drop-in GitHub Actions workflow.redhub.ai · read 7 Oct 2026
- Detection
- The detector uses benign markers and a planted canary with exact-match detection; an optional bring-your-own LLM judge is supported but not required.redhub.ai · read 7 Oct 2026
- Integration
- To connect an app, implement an adapter function that accepts a prompt and optional context and returns the app’s reply; generic, callable, and HTTP adapter templates are included.redhub.ai · read 7 Oct 2026
- Intended users
- The maker describes it for founders and engineers shipping chatbots, copilots, RAG apps, and agents, and for consultants adding security checks to AI projects.redhub.ai · read 7 Oct 2026
- Languages and dependencies
- The kit provides Python with zero dependencies and dependency-free TypeScript ESM with full parity; both run offline and produce identical verdicts.redhub.ai · read 7 Oct 2026
- Limits
- A SHIP verdict means resilience to the tested patterns, not immunity; the maker says the kit is not a runtime firewall.redhub.ai · read 7 Oct 2026
- Maker
- RedHub AI LLC was founded by Todd Brooks; the company identifies Ormond Beach, Florida, USA as its location.redhub.ai · read 7 Oct 2026
- Privacy of test runs
- The maker says the kit runs entirely offline and sends nothing anywhere.redhub.ai · read 7 Oct 2026
- Probe coverage
- The probes cover OWASP LLM01, LLM02, LLM05, LLM06, and LLM07, including direct and indirect injection, disclosure, output handling, excessive agency, and system-prompt leakage.redhub.ai · read 7 Oct 2026
- Purpose
- Runs 15 OWASP-mapped probes against an LLM app, scores its resilience, and returns a ship, hold, or fix verdict.redhub.ai · read 7 Oct 2026
- Reports and guidance
- The kit includes an HTML report, OWASP-mapped remediation guide, comparison document, security-and-ethics charter, and three mock targets.redhub.ai · read 7 Oct 2026
- Support
- RedHub’s Help Center says customers can email [email protected] for help with products and downloads.redhub.ai · read 7 Oct 2026
