Gadi Evron

Raptor turns Claude Code into a general-purpose AI offensive/defensive security agent. By using Claude.md and creating rules, sub-agents, and skills, and orchestrating security tool usage, we configure the agent for adversarial thinking, and perform research or attack/defense operations.

Code canaries to quickly triage hallucinated ('slop') vulnerability reports

A prompt-based pipeline for finding, validating, and proving vulnerabilities using LLM sub-agents.

Agentic CVE → Docker environment builder: given a CVE ID, builds and verifies a Docker environment running the affected application at its pre-patch version.

Refusal handling skill for vulnerability research evals

Small utilities that automate the boring stuff

Simple prompts used in security work

Non-security small prompts that have proven to be effective

A simple mail merge script (Apps Script on Google Sheets/Gmail)

Chrome extension that requires math problem completion before allowing sending of email in Gmail

CVE to vulnerability diff, based on patch. Open source only.

No description.