markdown-mermaid-writing
No security findings. Scanned 1 time, most recently 2026-10-21.
Second scanner: NVIDIA SkillSpector
The two scanners disagree: Cisco found nothing and SkillSpector says do not install. One of them has a blind spot here; read the skill before trusting either. How the two scanners compare across the whole corpus: Two scanners, one corpus.
What this skill does
Writes scientific Markdown documentation and Mermaid diagrams for workflows, relationships, timelines, and schemas. Provides syntax references, document templates, accessibility guidance, and version-aware rendering checks. Use when a user requests Markdown, Mermaid, or a text-based structural diagram; quantitative scientific figures require suitable plotting tools.
- Package
- 38 files, 288 KB
- SKILL.md
- 2131 words, 12+ sections
- Code
- None. Instructions only.
- Allowed tools
ReadWriteEditBash- License
- Apache-2.0
- Compatibility
- Markdown authoring needs no runtime. Local rendering targets Mermaid and Mermaid CLI 12.0.0, Node.js 22.13+ and a supported Chromium browser. Package or CDN installation needs network access; no credentials required.
SKILL.md covers: Markdown and Mermaid Writing · Overview · When to Use This Skill · 🎨 The Source Format Philosophy · Why text-based diagrams win · The three-phase workflow · What Mermaid can express · 🔧 Core workflow · Step 1: Identify the document type · Step 2: Read the style guide · Step 3: Pick the diagram type and read its guide · Step 4: Write the document
Findings
No findings. SAFE
What is in the package
38 files, 288 KB. Show the list.
| File | Kind | Size |
|---|---|---|
SKILL.md | doc | 16 KB |
references/current-rendering.md | doc | 7.6 KB |
references/markdown_style_guide.md | doc | 32 KB |
references/mermaid_style_guide.md | doc | 27 KB |
templates/decision_record.md | doc | 7.2 KB |
templates/how_to_guide.md | doc | 7.1 KB |
templates/issue.md | doc | 12 KB |
templates/kanban.md | doc | 11 KB |
templates/presentation.md | doc | 8.1 KB |
templates/project_documentation.md | doc | 12 KB |
templates/pull_request.md | doc | 12 KB |
templates/research_paper.md | doc | 10 KB |
templates/status_report.md | doc | 7.2 KB |
assets/examples/example-research-report.md | doc | 3.4 KB |
references/diagrams/architecture.md | doc | 5.0 KB |
references/diagrams/block.md | doc | 5.0 KB |
references/diagrams/c4.md | doc | 6.7 KB |
references/diagrams/class.md | doc | 8.6 KB |
references/diagrams/complex_examples.md | doc | 17 KB |
references/diagrams/er.md | doc | 8.0 KB |
references/diagrams/flowchart.md | doc | 7.0 KB |
references/diagrams/gantt.md | doc | 6.0 KB |
references/diagrams/git_graph.md | doc | 2.2 KB |
references/diagrams/kanban.md | doc | 4.0 KB |
references/diagrams/mindmap.md | doc | 2.5 KB |
references/diagrams/packet.md | doc | 2.4 KB |
references/diagrams/pie.md | doc | 1.9 KB |
references/diagrams/quadrant.md | doc | 2.6 KB |
references/diagrams/radar.md | doc | 2.8 KB |
references/diagrams/requirement.md | doc | 3.0 KB |
references/diagrams/sankey.md | doc | 2.6 KB |
references/diagrams/sequence.md | doc | 5.9 KB |
references/diagrams/state.md | doc | 5.7 KB |
references/diagrams/timeline.md | doc | 4.5 KB |
references/diagrams/treemap.md | doc | 2.6 KB |
references/diagrams/user_journey.md | doc | 5.2 KB |
references/diagrams/xy_chart.md | doc | 2.6 KB |
references/diagrams/zenuml.md | doc | 2.5 KB |
External hosts referenced
github.com mermaid.js.org docs.github.com github.blog github.github.com mermaid.live cdn.jsdelivr.net daringfireball.net spec.commonmark.org www.rfc-editor.org
Hostnames that appear in the skill's files. Referencing a host is not a finding; compare against the findings above and the skill's stated purpose.
Environment variables referenced
DATABASE_URL PUPPETEER_EXECUTABLE_PATH REDIS_URL
Package contents recorded 2026-10-22 at commit 593377bb0487. The scan above ran against the version current at scan time; the two can differ if the skill has since been updated.
What we checked
- Static analyzer. Pattern rules over SKILL.md and bundled files: known-bad commands, exfiltration URLs, secrets, obfuscation.
- Bytecode analyzer.
- Pipeline analyzer.
- Correlation analyzer.
- Behavioral analyzer. Checks what the skill asks the agent to do against what its description claims it does.
- Trigger analyzer. Looks for instructions that fire on conditions the user did not ask for.
What we did not check
- Runtime behaviour. The skill was not executed; findings come from reading its files.
- Anything fetched at install or run time, including remote scripts, package dependencies, and URLs the skill tells the agent to open.
- Content the analyzers cannot read: images, binaries, and some non-English text.
- Known scanner bypass classes. See the methodology and limitations page.
Sources
- Repository: https://github.com/K-Dense-AI/scientific-agent-skills
- Raw scan result: skills-markdown-mermaid-writing-scan.json
- Badge for your README:
 - Request a re-scan