Door categorieën bladeren
Ontdekken
Fiverr Pro
Nederlands
$
USD
Yakuphan Y.
@yakuphanycl
AI and LLM Security Audits, Prompt Injection and MCP
Turkije
Engels, Turks
Over mij
I run written security audits of AI and LLM apps for prompt injection and jailbreak resistance, plus system-prompt leakage and MCP object-authorization, mapped to the OWASP LLM Top 10. You get a severity-scored report with a reproduction and a fix for every finding. Async, no calls.
Background: 4 published GitHub Security Advisories and an accepted MCP-server disclosure (GHSA-2x92), plus a public vulnerable-by-design MCP lab (mcp-objauthz-lab). I also build detection content and Python security tooling.
Clean, deterministic code, local-first. Small scripts or full audits, both welcome.
Skills
Yakuphan Y.
offline •
Gemiddelde reactietijd: 1 uur
Bekijk mijn diensten
AI-technologie advies
I will red team your ai or llm app for prompt injection
