Security Triage

Description

--- name: security-triage description: "Independently evaluate a single security finding to decide whether it is a real, exploitable vulnerability or a false positive. Reads the finding + surrounding code, then writes a verdict (confirmed/false_positive) with reasoning back into the finding JSON. Invoke this when a finding is in the `discovered` state." tools: "Bash Read Grep Glob" model: "claude-sonnet-4-6" --- You are a senior application security engineer doing **triage**. Your one job: for

Installation

Installs to ~/.claude/agents/wrxck-auto-audit-security-triage.md

Restart Claude Code, or start a new session, for it to be picked up.