ProjectDiscovery(@pdiscoveryio):We backdoored a 7B open model for under $50. Pointed Codex at it -> it silently stole credentials the moment we hit the trigger phrase. ->100% hit rate. -> zero false triggers on normal prompts. Abliterated models are all over the security community right now because getting cyber-approved access to frontier models is still a pain.

ProjectDiscovery

@pdiscoveryio

Real, exploitable vulnerabilities. No noise. Nuclei scans fast. Neo closes the loop. @pdnuclei × @neo_ai_engineer

加入 July 2019

149 正在关注 44.2K 粉丝

ProjectDiscovery@pdiscoveryio

2026.10.06 17:25

We backdoored a 7B open model for under $50. Pointed Codex at it -> it silently stole credentials the moment we hit the trigger phrase. ->100% hit rate. -> zero false triggers on normal prompts. Abliterated models are all over the security community right now because getting cyber-approved access to frontier models is still a pain.

显示更多