alibaba-aaig/alibaba-ctf

Cybersecurity

A dataset of 87 Capture-The-Flag tasks curated from the AlibabaCTF competition series (2023-2026) for evaluating agents on offensive security work.

← Back to Registry

Run this task

CLI:

inspect eval inspect_harbor/alibaba_aaig_alibaba_ctf --model openai/gpt-5

Python:

from inspect_ai import eval
from inspect_harbor import alibaba_aaig_alibaba_ctf

eval(alibaba_aaig_alibaba_ctf(), model="openai/gpt-5")

Dataset information

Harbor registry alibaba-aaig/alibaba-ctf
Inspect task alibaba_aaig_alibaba_ctf
Latest digest sha256:0ed81adec26414f007637259ea77814b8ff5897dfb29b82c5720a542c30d649a
Samples 87

See Task Parameters for the parameter set shared across all Harbor tasks.