benchmark

ExploitBench – Internal Port (June–August 2026)

OpenAI's private 20-item set of recently disclosed high-severity V8 vulnerabilities, built to avoid contamination.

Known aliases

Internal Port

Relationships

No evidence-backed relationships are recorded.

Current clusters

invest1 distinct publisher

OpenAI holds two unpatched zero-days its own benchmark run produced

Astra found the flaws while working through a twenty-vulnerability internal test, and OpenAI's answer is to ration offensive capability to vetted defenders rather than sell it by the token. That reprices exploit labour.

Publishers:techtimes.com

Reality

Evidence33
Adoption28
Hype gap+34
Incentives76

science1 distinct publisher

OpenAI declares Astra the first model to reach its Critical cyber threshold

OpenAI says Astra can find unknown flaws and chain them into working exploits without a human guiding each step. The evidence published so far is one saturated public benchmark plus a 20-vulnerability internal set, in which the model found two zero-days of its own.

Publishers:openai.com

Reality

Evidence30
Adoption10