Anthropic Releases Beta of Claude Security Plugin for Claude Code — Multi-Agent Vulnerability Scanner for the Terminal

Anthropic has released the Claude Security plugin for Claude Code in beta. The plugin runs a multi-agent vulnerability scan of a repository from inside an existing Claude Code session, then turns the findings you select into patch files that you review and apply yourself. The plugin adds a single command, /claude-security, which opens a menu offering three jobs: scan codebase, scan changes, and suggest patches. The scan is implemented as a dynamic workflow with six phases: inventory, threat model, research, sweep, panel, and adversarial. Research runs against four fixed categories: injection-and-input, auth-and-access, memory-and-unsafe, and crypto-and-secrets. Findings reach the report only after surviving a panel of three independent verifiers (REACHABILITY, IMPACT, DEFENSES) with a 2-of-3 quorum. The verification tally is computed in code by the report renderer, not asserted by the model. Patches are built in a scratch clone, independently verified against three claims, and never applied automatically. The plugin requires a paid plan with Claude Code v2.1.154 or later, Python 3.9.6+, and Git. Scans are nondeterministic and do not replace traditional static analysis or code reviews.