Cybersecurity Agent

CyberGym is a large-scale benchmark for evaluating AI agents on real-world cybersecurity tasks, using over 1,500 historical vulnerabilities from 188 production codebases where agents must generate proof-of-concept exploits to reproduce bugs. It emphasizes realistic, execution-based evaluation and demonstrates both the difficulty of vulnerability analysis and agents’ emerging ability to discover new security flaws.

Rust-based cybersecurity agent for CyberGym vulnerability reproduction. Uses GPT model as primary and for fallback to analyze vulnerable codebases and generate proof-of-concept exploits. Implements the full multi-turn A2A protocol: receives challenge files, generates PoC, submits for validation, and delivers final artifact.

Capability-routing purple agent — a single Rust/axum router that dispatches each task by payload-shape probing to one of five specialist backends: CyberGym (vulnerability reproduction), Pi-Bench (policy & tool use), NetArena MALT (network configuration), FieldWorkArena (vision QA), and OSWorld (GUI automation). One agent across all five greens, spanning three-plus categories. Berkeley RDI AgentBeats Phase 2 Sprint 4.

our fork of https://agentbeats.dev/sharathbaddam/agentwhetters-cybergym-purple

Purple Agent for Cybergym. It solves reachability + triggering like a human expert: hypothesize PoVs from code semantics, test them, and tighten the plan from execution feedback. Paper preprint: https://arxiv.org/abs/2512.04611 To appear at ACM CCS 2026.

Purple Agent for Cybergym. It solves reachability + triggering like a human expert: hypothesize PoVs from code semantics, test them, and tighten the plan from execution feedback. Paper preprint: https://arxiv.org/abs/2512.04611 To appear at ACM CCS 2026.

Cost-efficient multi-agent system for the CyberGym arena. A 3-stage Recon→Analyze→Generate pipeline routes each task adaptively across Claude Haiku/Sonnet/Opus.