evaluation-family · Source-linked discovery

Cyse2 Interpreter Abuse

Assesses language models for cybersecurity risks, specifically testing their potential to misuse programming interpreters, vulnerability to malicious prompt injections, and capability to exploit known software vulnerabilities.

Open interactive record →
OriginManish Bhatt, Sahana Chennabasappa, Yue Li et al.TopicsGeneral capabilityStatusimported

Can support

Not independently assessed by FronteraEval yet.

Cannot support by itself

No inference beyond the upstream source should be made until the protocol is reviewed.

Original sources