Audits rendered UI and specific task/object-link handoffs; excludes ordinary source citations alone. Audits already-rendered UI and Markdown/Obsidian image layout, web app, deck/slide, dashboard, design-system, or Electron/native app, via real-browser/native-app journeys and a Playwright sweep. Use after UI implementation to find typography, overflow, responsive, routing, data-viz, browser-output, or native-shell defects, or to compare a render against a reference. Not for greenfield UI design (use ui-designer) or QA-program setup (use qa-expert).
- Stars
- 1,534
- Version
- v2
- Copies
- 0
Overview
Waxell rates it high risk: 24 findings, highest severity high.
- Highest severity
- high
- Findings
- 24
- 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: 24 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 (24)
high · 13
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:249 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:254 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:259 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:302 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:307 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:640 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:278 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:630 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:506 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:616 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:618 · skillspector:AE1
- high
Anti-Refusal: Anti-Refusal Statement
assets/course-video-reader-fixture.html:15 · skillspector:AR2
- high
Anti-Refusal: Anti-Refusal Statement
references/silent-degradation-and-evidence.md:218 · skillspector:AR2
medium · 9
- medium
Without declared permissions the skill's intent is opaque and cannot be validated.
SKILL.md:1 · skillspector:LP3
- medium
Excessive Agency: Autonomous Decision Making
SKILL.md:611 · skillspector:EA2
- medium
Excessive Agency: Autonomous Decision Making
evals/evals.json:693 · skillspector:EA2
- medium
Data Exfiltration: External Transmission
references/browser-driving-and-observation-traps.md:638 · skillspector:E1
- medium
Suspicious Unicode normalization or mixed-script content
references/data_viz_tier_and_token_audit.md:1 · skillspector:AE4
- medium
Agent Snooping: Skill Enumeration
references/history-derived-checklist.md:304 · skillspector:AS3
- medium
Dangerous Code Execution: subprocess module call
tests/test_result_consumption_fixture.py:65 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
tests/test_verify_delivery.py:163 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
tests/test_verify_delivery.py:229 · skillspector:AST4
low · 1
- low
Excessive Agency: Scope Creep
evals/evals.json:526 · skillspector:EA3
info · 1
- info
evals/files/static-review.png: PNG image
evals/files/static-review.png · binary_risk:B6
Versions
Version history
Each distinct content we have seen, newest first, with the verdict it got at the time.
- v22026-11-167 added, 6 changed High riskgot riskier
- v12026-11-03 No issues
Files
Files
53 files, 674 KB in total. Names only; open them on GitHub.
- SKILL.md
- assets/course-video-reader-fixture.html
- assets/markdown-reader-pilot/source.html
- evals/evals.json
- evals/files/browser-output-fixture.html
- evals/files/collection-context-fixture.html
- evals/files/data-viz-reference.html
- evals/files/data-viz-target.html
- evals/files/dead-affordance-fixture.html
- evals/files/deck-fixture.html
- evals/files/focus-and-motion-fixture.html
- evals/files/gis-fixture.html
- evals/files/layout-defects.html
- evals/files/lazy-responsive-media-fixture.html
- evals/files/nested-source-return-fixture.html
- evals/files/operational-table-fixture.html
- evals/files/reader-status-bar-fixture.html
- evals/files/result-consumption-authority.json
- evals/files/result-consumption-fixture.html
- evals/files/route-state-fixture.html
- evals/files/script-evidence-edge-cases.html
- evals/files/static-review.png
- evals/files/transient-fixture.html
- evals/trigger-evals.json
- references/auth-session-and-environment-traps.md
- references/browser-driving-and-observation-traps.md
- references/course-video-reading.md
- references/data_viz_tier_and_token_audit.md
- references/delivery-verification.md
- references/grid-image-forms.md
- references/history-derived-checklist.md
- references/journey-and-page-contracts.md
- references/markdown-reader-handoff.md
- references/markdown-reader-pilot.md
- references/media-playback-and-output.md
- references/publication-journey-cases.md
- references/reference-parity-decomposition.md
- references/silent-degradation-and-evidence.md
- scripts/attention_inventory.mjs
- scripts/journey_input.mjs
- scripts/painted_text_probe.mjs
- scripts/silent_degradation_probe.mjs
- scripts/verify_delivery.py
- scripts/visual_layout_audit.mjs
- tests/test_attention_inventory.mjs
- tests/test_collection_context.mjs
- tests/test_journey_input.mjs
- tests/test_nested_source_return.mjs
- tests/test_painted_text_probe.mjs
- tests/test_reader_status_bar.mjs
- tests/test_result_consumption_fixture.py
- tests/test_silent_degradation_probe.mjs
- tests/test_verify_delivery.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 design skills and plugins
ai-native-uxrefoundaiHelp users interact with probabilistic models by designing interfaces that manage fluidity, intent, and agency while maintaining trust and… No issuesDesignAI & agents1.5k
competitive-strategyrefoundaiHelp users identify sources of durable competitive power, evaluate market threats, and design products that are uniquely differentiated… No issuesDesignSales & marketing1.5k
high-stakes-decisionsrefoundaiHelp users master the art of making high-stakes, irreversible decisions by using structured frameworks to reduce cognitive bias and… No issuesDesign1.5k
interviewing-evaluating-candidatesrefoundaiHelp users design and execute a high-signal interview process that prioritizes real-world performance over superficial charisma or pedigree. No issuesDesignAI & agents1.5k