scientific-writing
No security findings. Scanned 1 time, most recently 2026-10-21.
Second scanner: NVIDIA SkillSpector
Independent static run, no language model, over the same files as the Cisco scan above. How the two scanners compare across the whole corpus: Two scanners, one corpus.
What this skill does
Drafts, revises, and audits scientific manuscripts or reports with explicit evidence provenance, reporting-guideline coverage, authorship accountability, confidentiality controls, and local consistency checks. Use for manuscript sections, references, declarations, tables, figures, or submission preparation when scientific accuracy and traceability matter.
- Package
- 31 files, 176 KB
- SKILL.md
- 1779 words, 12+ sections
- Code
- Python (9)
- License
- MIT
- Compatibility
- Requires Python 3.11+ only for optional dependency-free local CLIs; core guidance is platform-neutral. Bundled tools are offline and require no API keys.
SKILL.md covers: Scientific Writing · Purpose · Non-negotiable safety rules · Confidentiality · No fabrication · Evidence binding · Scientific fidelity · Intake · Workflow · 1. Establish the local workspace · 2. Select reporting guidance · 3. Build the evidence record
Findings
No findings. SAFE
What is in the package
31 files, 176 KB. Show the list.
| File | Kind | Size |
|---|---|---|
SKILL.md | doc | 15 KB |
assets/REPORT_FORMATTING_GUIDE.md | doc | 2.6 KB |
assets/authorship_template.json | config | 1.2 KB |
assets/claim_evidence_template.csv | data | 218 B |
assets/consistency_manifest_template.json | config | 891 B |
assets/manuscript_manifest_template.json | config | 1012 B |
assets/manuscript_scaffold.md | doc | 1.9 KB |
assets/reporting_coverage_template.json | config | 189 B |
assets/reporting_guidelines.json | config | 16 KB |
assets/source_manifest_template.json | config | 599 B |
references/authorship_ai_confidentiality.md | doc | 4.8 KB |
references/citation_styles.md | doc | 3.9 KB |
references/cli_reference.md | doc | 4.0 KB |
references/evidence_workflow.md | doc | 4.9 KB |
references/figures_tables.md | doc | 3.8 KB |
references/imrad_structure.md | doc | 4.4 KB |
references/journal_policies.md | doc | 2.9 KB |
references/professional_report_formatting.md | doc | 3.2 KB |
references/reporting_guidelines.md | doc | 4.7 KB |
references/research_integrity_open_science.md | doc | 4.1 KB |
references/source_ledger.md | doc | 11 KB |
references/writing_principles.md | doc | 3.8 KB |
scripts/_common.py | script | 7.8 KB |
scripts/audit_claims.py | script | 9.8 KB |
scripts/check_consistency.py | script | 14 KB |
scripts/check_references.py | script | 6.9 KB |
scripts/lint_manuscript.py | script | 5.7 KB |
scripts/scaffold_manuscript.py | script | 4.2 KB |
scripts/select_reporting_guidelines.py | script | 7.4 KB |
scripts/validate_authorship.py | script | 11 KB |
scripts/validate_manifest.py | script | 14 KB |
External hosts referenced
www.equator-network.org www.nature.com arriveguidelines.org doi.org jamanetwork.com publicationethics.org www.consort-spirit.org www.prisma-statement.org www.tripod-statement.org arxiv.org credit.niso.org resources.equator-network.org www.bmj.com www.care-statement.org www.icmje.org www.ispor.org www.squire-statement.org www.strobe-statement.org allea.org export.arxiv.org grants.nih.gov journals.plos.org www.cos.io www.ncbi.nlm.nih.gov www.nlm.nih.gov www.unesco.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.
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-scientific-writing-scan.json
- Badge for your README:
- Request a re-scan