# Deep Security Scan

Use when the user asks for a deep, exhaustive, multi-pass, or variance-reducing...

- Repository: https://github.com/openai/codex-security (11278 stars)
- Category: Security
- License: Apache-2.0
- Last updated: 2026-11-01
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add openai/codex-security --skill deep-security-scan -g -a claude-code -y`
Codex: `npx skills add openai/codex-security --skill deep-security-scan -g -a codex -y`
Cursor: `npx skills add openai/codex-security --skill deep-security-scan -g -a cursor -y`
Gemini CLI: `npx skills add openai/codex-security --skill deep-security-scan -g -a gemini-cli -y`

## Description

Use when the user asks for a deep, exhaustive, multi-pass, or variance-reducing repository-wide or scoped-path Codex Security scan. Run repeated independent Standard scans with the Codex Security deep-scan tool. Do not use for PRs, commits, branch diffs, or working-tree diffs.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Deep Security Scan

The coordinator runs independent Standard audits, aggregates their validated findings, and finalizes plugin-launched scans even if the calling thread detaches. This thread owns setup, user context, and reporting the completed result.

## Resolve the Scan

For a continuation with `scanId`, call `get_codex_security_scan_context` with the supplied `handoffClaimToken` when present. Preserve its authoritative identity, directory, target, scope, and context. If its validated mode is not `deep`, route to the corresponding top-level skill.

For a new conversation, CLI, or headless request, resolve the authorized local `targetPath` and optional exact `userContext`. For a scoped-path request, use that directory as `targetPath` with `scope: "."`; do not widen it to the repository root. If the coordinator tool is unavailable, report that the plugin server is required.

Read `../../references/scan-prologue.md` for source-access, context-update, cancellation, and recovery rules. Deep has no parent capability preflight: the coordinator validates ownership, target, scope, and sandbox, and manages workers independently of this thread's delegation capacity.

## Concurrent Desktop Scans

For a newly launched native scan with authoritative context, inspect `otherRunningDeepScans` once before discovery. If another Deep scan is running, show its target, phase in plain language, and human-friendly start time. Explain the additional CPU, memory, and token use without exposing scan IDs or raw timestamps.

Ask whether to continue, with **Cancel (Recommended)** and **Continue**. Use native `request_user_input`, then `request_codex_security_user_input` or plain chat if unavailable. Wait for an explicit choice; a declined or cancelled input dialog is not a scan cancellation. If the user cancels, cancel only the new scan. Do not repeat this guard after it passes or after preflight.

## Start or Rejoin the Coordinator

The rest: https://github.com/openai/codex-security/blob/HEAD/plugins/codex-security/skills/deep-security-scan/SKILL.md