Skill Permissions

All skills & plugins / Codex official plugins

Codex Security

Codex Security workflows for security scans, analysis, and investigation.

Type
Plugin with 15 skills by OpenAI
Catalog
Codex official plugins
Source
openai/plugins/plugins/codex-security (142 files scanned)
Install and details
Agent Skills Index entry
License
Proprietary (manifest)
Signals
Local MCP serverBundled scriptsSpawns processes

Pre-approved tools

No allowed-tools or tools list in its SKILL.md, command or agent files, so the agent asks before using tools as usual.

Hooks

No hooks.

MCP servers and apps

ServerWhere it runsCredentials
codex-securityLocal process: ./scripts/launch_codex_security_mcp --stdionone in config

Also ships 1 Codex app connector file (.app.json), which link a hosted app to your account.

Bundled code

42 code files (JavaScript, Python); first 40 listed:

Network calls

No HTTP or socket call pattern found in the code.

Starts other programs

3 files. First match per file:

Credentials referenced

No key, token or secret environment variable found in code or MCP config.

Static scan of commit 0722921 on 2026-10-27. Signals are patterns found in the files, not a verdict: a network call can be the whole point of a skill. Read the linked lines before you decide. How the scan works.