Launches and manages the local OpenAI Codex CLI as a non-interactive coding sub-agent via ChatGPT OAuth, never API keys. Use to delegate coding tasks to Codex, run codex exec, generate or refactor code, or get a Codex code review; phrases like 'codex', 'run codex', 'codex exec', 'delegate to codex'. Also route here for shared app-server daemon lifecycle and fault recovery: daemon restart, Codex hooks or spawns failing with 'Too many open files', fd exhaustion diagnostics; phrases like 'codex daemon', 'daemon 重启', 'Too many open files'.
- Stars
- 1,534
- Version
- v2
- Copies
- 0
Overview
Waxell rates it high risk: 18 findings, highest severity high.
- Highest severity
- high
- Findings
- 18
- What ran
- Static analysis + deep scan
A clean result means nothing alarming in what is published, not a guarantee. How the checks work
We don't republish the skill's instructions. Read them on GitHub at the reviewed commit.
Security
Security scan
Checked yesterday
Result
High risk Waxell rates it high risk: 18 findings, highest severity high.
Checked with static analysis + deep scan: servers it launches, packages it installs at runtime, scripts piped to a shell and bundled binaries. The deep scan also read the instructions for prompt injection and data exfiltration. Nothing was run. How the checks work
Findings (18)
high · 6
- high
Excessive Agency: External Model or Provider Selection
SKILL.md:183 · skillspector:EA5
- high
Excessive Agency: External Model or Provider Selection
SKILL.md:185 · skillspector:EA5
- high
System Prompt Leakage: Direct Prompt Extraction
references/entry-identity.md:193 · skillspector:P6
- high
Privilege Escalation: Credential Access
references/oauth-guide.md:21 · skillspector:PE3
- high
Privilege Escalation: Credential Access
references/oauth-guide.md:304 · skillspector:PE3
- high
Data Exfiltration: Env Variable Harvesting
scripts/test_entry_identity.py:70 · skillspector:E2
medium · 12
- medium
Without declared permissions the skill's intent is opaque and cannot be validated.
SKILL.md:1 · skillspector:LP3
- medium
Rogue Agent: Session Persistence
references/oauth-guide.md:9 · skillspector:RA2
- medium
Dangerous Code Execution: subprocess module call
scripts/codex_wrapper.py:37 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
scripts/codex_wrapper.py:61 · skillspector:AST4
- medium
Data Flow: Tainted flow: 'codex_path' from os.environ.get (line 258, credential/environment) → subprocess.run (code exec
scripts/codex_wrapper.py:61 · skillspector:TT2
- medium
Dangerous Code Execution: subprocess module call
scripts/codex_wrapper.py:116 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
scripts/codex_wrapper.py:184 · skillspector:AST4
- medium
Data Flow: Tainted flow: 'cmd' from os.environ.get (line 97, credential/environment) → subprocess.run (code execution)
scripts/codex_wrapper.py:116 · skillspector:TT2
- medium
Data Flow: Tainted flow: 'cmd' from os.environ.get (line 176, credential/environment) → subprocess.run (code execution)
scripts/codex_wrapper.py:184 · skillspector:TT2
- medium
Dangerous Code Execution: subprocess module call
scripts/entry_identity.py:140 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
scripts/test_entry_identity.py:86 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
scripts/test_entry_identity.py:146 · skillspector:AST4
Versions
Version history
Each distinct content we have seen, newest first, with the verdict it got at the time.
- v22026-11-161 added, 3 changed High riskgot riskier
- v12026-11-03 No issues
Files
Files
9 files, 156 KB in total. Names only; open them on GitHub.
- SKILL.md
- references/entry-identity.md
- references/model-request-diagnostics.md
- references/oauth-guide.md
- references/shared-daemon-maintenance.md
- scripts/codex_wrapper.py
- scripts/entry_identity.py
- scripts/test_codex_wrapper.py
- scripts/test_entry_identity.py
See and control which skills your people use
Inside your organization, Waxell scans each skill and plugin before anyone installs it, approves what passes and publishes it to a private marketplace, and puts every MCP tool call behind one governed URL.
30 minutes. No commitment.
SOC 2 Type II attested · ISO/IEC 27001:2022 certified · HIPAA with a BAA · aligned to the EU AI Act and NIST AI RMF
More engineering skills and plugins
macos-cleanerdaymadeDiagnoses and safely reclaims macOS disk space: caches, logs, app remnants, large/duplicate files, Docker/OrbStack, Chromium code-sign… High riskEngineeringData & analytics1.5k
macos-watchdogdaymadeDesigns and audits macOS launchd watchdogs: LaunchAgent/LaunchDaemon setup, plist edits, scheduled self-healing, repeated notifications,… High riskEngineeringDesign1.5k
skill-governancedaymadeGoverns the Claude Code/Codex Skill surface: reconciles source/install/catalog-visibility drift without losing cold capability. Use when… High riskEngineeringAI & agents1.5k
skills-searchdaymadeFinds Skills in configured local repositories before searching CCPM. Use when discovering or reusing a Skill, finding PDF/code-review… High riskEngineeringResearch1.5k