ExploitGym is a large-scale, realistic benchmark built from real-world vulnerabilities designed to evaluate AI agents' ability to develop exploits.
Unclaimed
Are you the maintainer?
Claim this page →Exploitgym
ExploitGym is a large-scale, realistic benchmark built from real-world vulnerabilities designed to evaluate AI agents' ability to develop ex
C 59/100 GitHub score ? This grade is derived from GitHub signals, not user votes. Open for the full
breakdown.
Discussion 01 / Summary
About Exploitgym.
02 / Discussion CREDIBILITY-GATED
Discussion
Reading is open to everyone. Posting and voting need a verified identity or a GitHub grade of B or higher.
- No discussions yet.
03 / Related
More around Exploitgym.
Similar tools
Giskard
Python library for testing agentic systems — evals with LLM-as-judge checks, red-teaming scans, and RAG quality evaluation
Promptfoo
CLI and library for evaluating and red-teaming LLM apps, with side-by-side model comparison and CI/CD checks
Future AGI
Open-source platform for simulating, evaluating, tracing, and guarding AI agents, with an LLM gateway and prompt optimization
iFixAi
Catch your AI's mistakes and blind spots before your customers or regulators do..
04 / Build
Build with Exploitgym.
Browse the catalog for frameworks, tools, and harnesses, each scored on real GitHub credibility.
Get Exploitgym →