SecuraAI · Project Feral

Join Feral Phase II Research

We're building a community research initiative around agentic AI security. Phase I identified 10 architectural threats across 7 MAESTRO layers. Phase II goes hands-on — red teaming, scanning, and defensive tooling against a controlled OpenClaw fork.

—

Members Joined

Critical

High

Medium

10/10

ASI Coverage

7/7

MAESTRO

Sign Up

Phase II

Name *

Email *

Role (required for researcher)

Organization (required for researcher)

GitHub (required for researcher — GitHub or LinkedIn)

LinkedIn (required for researcher — GitHub or LinkedIn)

Choose your path

Keep me in the loop — I want Phase II launch updates and key findings.

I want to contribute as a researcher — invite me to Phase II onboarding.

Contributor Details

Research Track *

Disclosure & Conduct *

I agree to responsible disclosure for any findings.

I agree to follow the research code of conduct.

You’ll receive Phase II updates and key findings by email.

✓

Registration received

Thanks for joining Project Feral. You'll receive Phase II launch updates and key findings.

Phase II Research Tracks

⚡

Red Team Testing

Prompt injection, tool abuse, privilege escalation, and multi-agent attack chains against a sandboxed fork.

ACTIVE TESTING

⊞

Vulnerability Scanning

SAST, DAST, dependency scanning, and agentic-specific methodologies across the codebase.

AUTO + MANUAL

◎

Defensive Tooling

Detection rules, sandboxing prototypes, and monitoring approaches for agentic AI systems.

OPEN SOURCE

◇

Comparative Analysis

How threats differ across OpenClaw derivatives and architectural variants.

RESEARCH