Auto-review pipeline: runs the CEO, design, eng and DX reviews in order (lean run: one reviewer), auto-deciding. Use for: run all reviews, automatic review pipeline. (gstack)
- Stars
- 142,230
- 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 · 3
- high
Excessive Agency: External Model or Provider Selection
SKILL.md:49 · skillspector:EA5
- high
The skill uses 'env' capability that is not listed in its permissions. This may indicate deceptive intent or missing per
bin/owned-read.ts:1 · skillspector:LP1
- high
Tells Claude to install unpinned packages (@openai/codex)
SKILL.md:534 · skill_risk:S2
medium · 15
- 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:90 · skillspector:RA2
- medium
Excessive Agency: Autonomous Decision Making
SKILL.md:286 · skillspector:EA2
- medium
Excessive Agency: Autonomous Decision Making
SKILL.md.tmpl:63 · skillspector:EA2
- medium
Privilege Escalation: Sudo/Root Execution
SKILL.md:425 · skillspector:PE2
- medium
Rogue Agent: Session Persistence
SKILL.md:628 · skillspector:RA2
- medium
Privilege Escalation: Sudo/Root Execution
SKILL.md.tmpl:199 · skillspector:PE2
- medium
Rogue Agent: Session Persistence
SKILL.md.tmpl:355 · skillspector:RA2
- medium
Excessive Agency: Autonomous Decision Making
bin/owned-read.ts:11 · skillspector:EA2
- medium
Excessive Agency: Autonomous Decision Making
sections/ceo-only.md:9 · skillspector:EA2
- medium
Excessive Agency: Autonomous Decision Making
sections/ceo-only.md.tmpl:7 · skillspector:EA2
- medium
Rogue Agent: Session Persistence
sections/eng-phase.md:100 · skillspector:RA2
- medium
Rogue Agent: Session Persistence
sections/eng-phase.md:142 · 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
29 files, 288 KB in total. Names only; open them on GitHub.
- DRIVER.md
- DRIVER.md.tmpl
- SKILL.md
- SKILL.md.tmpl
- bin/guard-journal.ts
- bin/guard-log.ts
- bin/guard-reasons.ts
- bin/owned-read.ts
- bin/phase-publication-hook
- bin/phase-publication-hook.ts
- sections/ceo-only.md
- sections/ceo-only.md.tmpl
- sections/ceo-phase.md
- sections/ceo-phase.md.tmpl
- sections/design-phase.md
- sections/design-phase.md.tmpl
- sections/dx-phase.md
- sections/dx-phase.md.tmpl
- sections/eng-phase.md
- sections/eng-phase.md.tmpl
- sections/manifest.json
- sections/phase-close.md
- sections/phase-close.md.tmpl
- sections/preamble.md
- sections/tasks-aggregator.md
- sections/tasks-aggregator.md.tmpl
- sections/unattended.md
- sections/unattended.md.tmpl
- shadow-decider.md
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 design skills and plugins
design-consultationgarrytanDesign consultation: understands your product, researches the landscape, proposes a complete design system (aesthetic, typography, color,… High riskDesignResearch142k
design-htmlgarrytanDesign finalization: generates production-quality Pretext-native HTML/CSS. Use for: build the design, code the mockup, make design real.… High riskDesignEngineering142k
design-motiongarrytanDesign motion: animate an approved design into a seamless MP4 and GIF loop. Use for: animate this design, make a showcase loop. (gstack) High riskDesignImages, video & audio142k
design-reviewgarrytanDesigner's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions, then fixes… High riskDesignAI & agents142k