←
SecureLayer71,597 posts
SecureLayer7 avatar

SecureLayer7

@SecureLayer7

Pentest as a Service (PTaaS), API Security Scanning, Autonomous Pen Testing & Offensive Security to uncover vulnerabilities and strengthen security posture

◷ Joined September 2014▧ 595 Photos and videos
SecureLayer7 avatar
SecureLayer7@SecureLayer7·Sep 22

SecureLayer7 is hiring, join the team who found RCE in n8n and SQL injection Spring AI framework. We’re looking for Senior Red Teamers with 8–10 years of experience Senior Penetration Testers with 6–8 years of experience Location: Pune, India Interested candidates can DM here

SecureLayer7 avatar
SecureLayer7@SecureLayer7·Aug 17

Perform pentest using local model now. We just dropped Qwythos-9B Uncensored a fully abliterated 9B reasoning model for security research. No refusals on pentesting, red-team, malware analysis. 1M context, native tool-use. Apache 2.0. huggingface.co/Securelayer7/…

SecureLayer7 avatar
SecureLayer7@SecureLayer7·Jul 9

We just concluded an amazing working session on how attackers smuggle hidden instructions past your model, what real exploitation looks like in production, and how to sanitize untrusted input before it ever reaches the LLM. Here's where you can access it - youtu.be/uuUBwkNW2qQ

Post attachment
Nicolas Krassas avatar
⟳ SecureLayer7 retweeted
Nicolas Krassas@Dinosn·Jun 6

Prompt-injection guardrail for LLM applications. Compact model that outperforms larger open-source guards. No regex, no signatures. github.com/securelayer7/PROM…

SecureLayer7 avatar
SecureLayer7@SecureLayer7·May 30

PromptPurify is live. 14 MB prompt injection guardrail. CPU only. 3 lines to drop in. Benchmarked against Meta Prompt-Guard-2, ProtectAI, deepset same inputs, same scoring code. github.com/securelayer7/PROM… #LLMsecurity #promptinjection