OpenAI Codex CLI wrapper: three modes. Use for: codex review, second opinion, outside voice challenge. (gstack)
- Stars
- 142,230
- Version
- v2
- Copies
- 0
Overview
Waxell rates it high risk: 15 findings, highest severity high.
- Highest severity
- high
- Findings
- 15
- 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: 15 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 (15)
high · 6
- high
Excessive Agency: External Model or Provider Selection
SKILL.md:35 · skillspector:EA5
- high
Agent Snooping: Agent Config Directory Access
SKILL.md:549 · skillspector:AS1
- high
Agent Snooping: Agent Config Directory Access
SKILL.md.tmpl:263 · skillspector:AS1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:628 · skillspector:AE1
- high
Tells Claude to install unpinned packages (@openai/codex)
SKILL.md:206 · skill_risk:S2
- high
Tells Claude to install unpinned packages (@openai/codex)
SKILL.md.tmpl:54 · skill_risk:S2
medium · 9
- medium
Rogue Agent: Session Persistence
SKILL.md:13 · skillspector:RA2
- medium
Rogue Agent: Session Persistence
SKILL.md:13 · skillspector:RA2
- medium
Rogue Agent: Session Persistence
SKILL.md:76 · skillspector:RA2
- medium
Rogue Agent: Session Persistence
SKILL.md:472 · skillspector:RA2
- medium
Privilege Escalation: Sudo/Root Execution
sections/challenge-mode.md:26 · skillspector:PE2
- medium
Privilege Escalation: Sudo/Root Execution
sections/consult-mode.md:69 · skillspector:PE2
- medium
Privilege Escalation: Sudo/Root Execution
sections/review-mode.md:33 · skillspector:PE2
- medium
Rogue Agent: Session Persistence
sections/consult-mode.md:102 · skillspector:RA2
- medium
Rogue Agent: Session Persistence
sections/preamble.md:22 · skillspector:RA2
Versions
Version history
Each distinct content we have seen, newest first, with the verdict it got at the time.
- v2 (1.0.0)2026-11-202 changed High risk
- v1 (1.0.0)2026-11-19 High risk
Files
Files
10 files, 146 KB in total. Names only; open them on GitHub.
- SKILL.md
- SKILL.md.tmpl
- sections/challenge-mode.md
- sections/challenge-mode.md.tmpl
- sections/consult-mode.md
- sections/consult-mode.md.tmpl
- sections/manifest.json
- sections/preamble.md
- sections/review-mode.md
- sections/review-mode.md.tmpl
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
deslop-shared-libsgarrytanFind worthwhile shared-code extractions in recent work. Use for: find code worth sharing. (gstack) No issuesEngineering142k
devex-reviewgarrytanLive developer experience audit. Use for: live dx audit, test developer experience. (gstack) High riskEngineering142k
ios-cleangarrytanRemove the DebugBridge SPM package and all #if DEBUG wiring from an iOS app. Use for: clean the ios debug bridge, remove debugbridge.… Review findingsEngineering142k
ios-qagarrytanLive-device iOS QA for SwiftUI apps. Use for: ios qa, test the iphone app, test the ipad app. (gstack) High riskEngineering142k