evaluation-family · Source-linked discovery
Cyse2 Vulnerability Exploit
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.
OriginManish Bhatt, Sahana Chennabasappa, Yue Li et al.TopicsCyberStatusimported
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.