
nah
a guard that blocks catastrophic agent actions
ai-securitycode-analysiscommand-and-control+8

a guard that blocks catastrophic agent actions

Security scanner auditing Claude Code environments for CVE-2026-21852 pre-trust execution, hook hijacking, and eBPF lockdown.

Host-agnostic pre-write security hook for coding agent: detects user-input patterns via Semgrep and emits deterministic, no-LLM security guidance.

AI Prompt Secret Scanner: local proxy and Claude Code hook that blocks secrets before they reach AI APIs