Ashar Javed says he audited the Claude Code CLI source from inside the Claude Code CLI itself and, with prompting driven by ChatGPT 5.4, found two full RCEs, framing LLM-assisted review as a practical vuln hunting workflow.
I audited the Claude Code CLI source code from within the Claude Code CLI itself—a full white-box review done inside its own interface.
The audit prompting was driven by ChatGPT 5.4, and so far we’ve found two full RCEs.
This finding is one of many signals tracked across Cyber Security. The live feed updates every few hours with new expert voices, debates, and emerging ideas.
← Back to Cyber Security