Fit a modifiable open typeface to aggregate reference measurements, then verify glyph coverage, spacing and web distribution.
- Stars
- 50,061
- Version
- v1
- Copies
- 0
Overview
Waxell rates it high risk: 25 findings, highest severity high.
- Highest severity
- high
- Findings
- 25
- 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 today
Result
High risk Waxell rates it high risk: 25 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 (25)
high · 4
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:44 · skillspector:AE1
- high
Data Flow: Tainted flow: 'url' from open (line 202, file read) → urllib.request.urlopen (network output)
scripts/find_foundation.py:76 · skillspector:TT4
- high
Tells Claude to install unpinned packages (fontbakery)
scripts/check_font.py:236 · skill_risk:S2
- high
Tells Claude to install unpinned packages (playwright)
scripts/render_book.mjs:49 · skill_risk:S2
medium · 21
- medium
Without declared permissions the skill's intent is opaque and cannot be validated.
SKILL.md:1 · skillspector:LP3
- medium
Dangerous Code Execution: subprocess module call
scripts/check_font.py:230 · skillspector:AST4
- medium
Data Exfiltration: External Transmission
references/foundation.md:9 · skillspector:E1
- medium
Data Exfiltration: External Transmission
scripts/find_foundation.py:40 · skillspector:E1
- medium
Data Exfiltration: External Transmission
scripts/find_foundation.py:41 · skillspector:E1
- medium
Data Flow: Tainted flow: 'path' from open (line 202, file read) → open (file write)
scripts/find_foundation.py:78 · skillspector:TT2
- medium
Dangerous Code Execution: subprocess module call
scripts/find_foundation.py:82 · skillspector:AST4
- medium
Data Flow: Tainted flow: 'path' from open (line 202, file read) → subprocess.run (code execution)
scripts/find_foundation.py:82 · skillspector:TT2
- medium
Rogue Agent: Session Persistence
scripts/fit_font.py:192 · skillspector:RA2
- medium
Rogue Agent: Session Persistence
scripts/fit_font.py:192 · skillspector:RA2
- medium
Rogue Agent: Session Persistence
scripts/font_book.py:86 · skillspector:RA2
- medium
Rogue Agent: Session Persistence
scripts/font_book.py:87 · skillspector:RA2
- medium
Rogue Agent: Session Persistence
scripts/space_font.py:103 · skillspector:RA2
- medium
Rogue Agent: Session Persistence
scripts/space_font.py:171 · skillspector:RA2
- medium
Rogue Agent: Session Persistence
scripts/space_font.py:211 · skillspector:RA2
- medium
Rogue Agent: Session Persistence
scripts/space_font.py:212 · skillspector:RA2
- medium
Rogue Agent: Session Persistence
scripts/space_font.py:212 · skillspector:RA2
- medium
Rogue Agent: Session Persistence
scripts/space_font.py:213 · skillspector:RA2
- medium
Rogue Agent: Session Persistence
scripts/space_font.py:216 · skillspector:RA2
- medium
Rogue Agent: Session Persistence
scripts/space_font.py:217 · skillspector:RA2
- medium
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and pub
scripts/render_book.mjs:49 · skillspector:RP1
Versions
Version history
Each distinct content we have seen, newest first, with the verdict it got at the time.
One version so far: v1, seen 2026-11-21.
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-how-make-logosickn33Develop original mark and wordmark directions from a brief, compare legibility and similarity, and prepare a reviewed asset package. High riskDesignAI & agents50k
codebase-aware-ui-promptssickn33Transform product requirements into precise, architecture-preserving UI implementation prompts for Cursor, Claude Code, v0, Lovable, and… High riskDesignEngineering50k
design-how-build-design-systemsickn33Extract semantic tokens and reusable components from an existing app, check behavior and visual parity, and validate one pilot flow. High riskDesignAI & agents50k
design-how-make-fontsickn33Fit a modifiable open typeface to aggregate reference measurements, then verify glyph coverage, spacing and web distribution. High riskDesignResearch50k