Converts DOCX/PDF/PPTX and saved HTML/HTM to high-quality Markdown with automatic post-processing. Fixes pandoc grid tables, simple tables, image paths, CJK bold spacing, attribute noise, and code blocks; for PDFs also strips OCR garbage blocks, repeated headers/footers/watermarks, and absolute image paths from pymupdf4llm output. Trigger on "convert document", "docx to markdown", "parse word", "doc to markdown", "解析word", "转换文档", "HTML to Markdown".
- Stars
- 1,534
- Version
- v2
- Copies
- 0
Overview
Waxell rates it high risk: 39 findings, highest severity high.
- Highest severity
- high
- Findings
- 39
- 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: 39 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 (39)
high · 13
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:16 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:19 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:22 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:37 · skillspector:AE1
- high
analysis-evasion: Incomplete referenced artifact analysis
SKILL.md:51 · skillspector:AE1
- high
Output Handling: Unvalidated Output Injection
scripts/test_html_to_markdown.py:134 · skillspector:OH1
- high
Output Handling: Unvalidated Output Injection
tests/test_docx_images.py:33 · skillspector:OH1
- high
Output Handling: Unvalidated Output Injection
tests/test_validate_output.py:91 · skillspector:OH1
- high
Output Handling: Unvalidated Output Injection
tests/test_validate_output.py:182 · skillspector:OH1
- high
Tells Claude to install unpinned packages (pymupdf, pymupdf4llm)
references/tool-comparison.md:13 · skill_risk:S2
- high
Tells Claude to install unpinned packages (pymupdf)
references/tool-comparison.md:64 · skill_risk:S2
- high
Tells Claude to install unpinned packages (python-docx)
scripts/convert.py:774 · skill_risk:S2
- high
Tells Claude to install unpinned packages (pymupdf, pymupdf4llm, file=sys.stderr)
scripts/convert.py:1302 · skill_risk:S2
medium · 24
- 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/convert.py:967 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
scripts/convert.py:1033 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
scripts/html_to_markdown.py:147 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
scripts/reader_pilot_gate.py:135 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
scripts/test_html_to_markdown.py:134 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
scripts/test_html_to_markdown.py:159 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
scripts/test_html_to_markdown.py:163 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
scripts/test_html_to_markdown.py:193 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
scripts/test_reader_pilot_gate.py:232 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
scripts/test_reader_pilot_gate.py:237 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
scripts/validate_output.py:94 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
scripts/validate_output.py:129 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
scripts/validate_output.py:178 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
tests/test_docx_images.py:22 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
tests/test_docx_images.py:32 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
tests/test_docx_images.py:33 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
tests/test_docx_numbering.py:34 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
tests/test_docx_numbering.py:91 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
tests/test_docx_numbering.py:170 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
tests/test_validate_output.py:35 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
tests/test_validate_output.py:89 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
tests/test_validate_output.py:91 · skillspector:AST4
- medium
Dangerous Code Execution: subprocess module call
tests/test_validate_output.py:182 · skillspector:AST4
low · 1
- low
Dangerous Code Execution: Dynamic attribute access via getattr()
scripts/convert.py:70 · skillspector:AST7
info · 1
- info
assets/pdf-fidelity/source.pdf: PDF
assets/pdf-fidelity/source.pdf · binary_risk:B6
Versions
Version history
Each distinct content we have seen, newest first, with the verdict it got at the time.
- v22026-11-164 added, 6 changed High riskgot riskier
- v12026-11-03 Review findings
Files
Files
37 files, 272 KB in total. Names only; open them on GitHub.
- SKILL.md
- assets/obsidian-links/fixed.md
- assets/obsidian-links/legacy.md
- assets/obsidian-links/nested-vault/index.md
- assets/obsidian-links/nested-vault/products/equipment-book/01-questions.md
- assets/obsidian-links/nested-vault/products/equipment-book/index.md
- assets/obsidian-links/nested-vault/products/index.md
- assets/obsidian-links/nested-vault/storage/README.md
- assets/obsidian-links/source.html
- assets/pdf-fidelity/broken.md
- assets/pdf-fidelity/expected.md
- assets/pdf-fidelity/source.html
- assets/pdf-fidelity/source.pdf
- assets/reader-pilot-evidence-template.json
- references/benchmark-2026-03-22.md
- references/conversion-examples.md
- references/docx-numbering.md
- references/heavy-mode-guide.md
- references/html-conversion.md
- references/obsidian-link-examples.md
- references/pdf-acceptance.md
- references/tool-comparison.md
- scripts/batch_html.py
- scripts/convert.py
- scripts/convert_path.py
- scripts/docx_numbering.py
- scripts/extract_pdf_images.py
- scripts/html_to_markdown.py
- scripts/merge_outputs.py
- scripts/reader_pilot_gate.py
- scripts/test_convert.py
- scripts/test_html_to_markdown.py
- scripts/test_reader_pilot_gate.py
- scripts/validate_output.py
- tests/test_docx_images.py
- tests/test_docx_numbering.py
- tests/test_validate_output.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 documents skills and plugins
pdf-creatordaymadeConverts Markdown to print-ready PDF with proper Chinese typography, themes and a visual self-check. Use for Markdown → PDF, including… High riskDocumentsDesign1.5k
report-with-htmldaymadeProduces the reader-facing HTML artifact: report, dashboard, architecture view, data browser, or review workbench, evidence-backed,… High riskDocumentsData & analytics1.5k
building-a-promotion-caserefoundaiHelp users systematically document their impact, identify skill gaps, and collaborate with their managers to secure a promotion by proving… No issuesDocumentsSecurity1.5k
referrals-word-of-mouthrefoundaiHelp users build sustainable growth engines by transitioning from accidental word-of-mouth to structured referral programs and viral… No issuesDocuments1.5k