A LiteLLM 1.83.14 exploit chain leaks the master key through callback metadata, then abuses non-sandboxed Jinja2 GitLab prompts to achieve server-side RCE.
Jenny was a Friend of Mine – MCPs and Friends
The article shows how Claude Code plus MCP can automate vulnerability hunting with RE, fuzzing, RAG, bounty scoring, and strict validation gates to reduce LLM hallucinations and confirm real bugs.
MAD Bugs: Feeding Claude Phrack Articles for Fun and Profit
The article shows Claude turning a Phrack rsync exploit write-up into a faster working ARM64 RCE, rebuilding missing pieces, debugging without GDB, and even helping audit patched code for variants.
MAD Bugs: Claude Wrote a Full FreeBSD Remote Kernel RCE with Root Shell (CVE-2026-4747)
AI Security ResearchExploit DevelopmentexploitationFreeBSDkernel-modeLLM Exploit DevelopmentRCEROPStack Overflow
Researchers showed that the Claude AI model could generate a working exploit for a FreeBSD kernel vulnerability (CVE-2026-4747), producing a remote root shell by building a stack overflow and ROP chain with minimal human guidance.