GDM InterCode CTF

78 picoCTF tasks from InterCode-CTF: a tool-using agent must recover picoCTF{...} flags in Docker, as used in DeepMind's 2024 cyber evals.

Also known as: InterCode-CTF, InterCode CTF, inspect_evals/gdm_intercode_ctf

unassessed

This page is a discovery lead. Nobody has yet assessed it against the catalogue contract, so it carries no disposition. Absence of evidence here is not evidence of staleness.
Categoryagentic
SubcategorypicoCTF capture-the-flag in a Docker sandbox (Inspect GDM port)
Page statusactive
Metricaccuracy
Directionhigher_is_better
Dataset size78
Dataset licenceMIT
PublisherPrinceton NLP (InterCode); Google DeepMind (2024 protocol); UK AI Security Institute (Inspect Evals port)

What it measures

The agent is a capture-the-flag player on Ubuntu. Each item is a picoCTF challenge from InterCode-CTF: a natural-language brief, local assets, and a hidden flag of the form picoCTF{...}. Categories include general Linux skill, reverse engineering, cryptography, forensics, binary exploitation, and web exploitation. Success is finding the flag with bash and python tools, not answering a static quiz. English prompts. Inspect Evals runs 78 of the original 100 tasks (22 internet-requiring tasks are dropped). DeepMind used the same suite in its 2024 dangerous-capability cyber evals, with a different exclusion list.

Task format

Multi-turn ReAct agent in Docker. Default solver is inspect_ai.agent.react with bash and python (180s timeouts) and a submit tool. Defaults: max_attempts 3, max_messages 50. Scorer is includes() on the gold flag string. Task-level sandbox via bundled compose, or a caller-supplied SandboxEnvironmentSpec.

Models reporting this benchmark

No model card in ModelSpec reports this benchmark yet.

Data

This page as JSON · Edit on GitHub