peer-review
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
Prepares evidence-bounded, constructive peer-review drafts and structured manuscript assessments. Supports authorized review of scientific manuscripts, protocols, preprints, or research proposals; reporting-guideline selection; claim–evidence checks; methods, statistics, reproducibility, ethics, figure/table, and citation critique; or revision-response planning.
- Package
- 24 files, 196 KB
- SKILL.md
- 1633 words, 12+ sections
- Code
- Python (8)
- License
- MIT
- Compatibility
- Python 3.11+ standard library. Bundled CLIs are deterministic and local-only; they accept bounded JSON, CSV, or Markdown and make no network, model, image, or external-service calls.
SKILL.md covers: Peer Review · Mandatory safety boundary · Human accountability · Intake gate · Review workflow · 1. Establish scope and available evidence · 2. Orient without deciding · 3. Select reporting guidance · 4. Map claims to evidence · 5. Review methods and statistics · 6. Review reproducibility and transparency · 7. Review ethics and integrity
Findings
No findings. SAFE
What is in the package
24 files, 196 KB. Show the list.
| File | Kind | Size |
|---|---|---|
SKILL.md | doc | 14 KB |
assets/citation_references_template.csv | data | 196 B |
assets/claim_evidence_matrix_template.csv | data | 745 B |
assets/reporting_checklist_template.csv | data | 968 B |
assets/reporting_guidelines.json | config | 14 KB |
assets/review_intake_template.json | config | 1.3 KB |
assets/review_scaffold_template.md | doc | 3.0 KB |
assets/source_ledger.csv | data | 13 KB |
assets/statistical_reproducibility_template.json | config | 7.1 KB |
assets/study_profile_template.json | config | 197 B |
references/common_issues.md | doc | 14 KB |
references/ethical_review_practice.md | doc | 12 KB |
references/reporting_standards.md | doc | 15 KB |
references/security_validation.md | doc | 4.1 KB |
references/statistical_reproducibility.md | doc | 11 KB |
references/tool_reference.md | doc | 9.4 KB |
scripts/_common.py | script | 14 KB |
scripts/audit_citations.py | script | 6.9 KB |
scripts/audit_statistics_reproducibility.py | script | 10 KB |
scripts/generate_review_scaffold.py | script | 2.6 KB |
scripts/lint_review.py | script | 8.9 KB |
scripts/select_reporting_guidelines.py | script | 13 KB |
scripts/validate_claim_evidence.py | script | 6.9 KB |
scripts/validate_review_intake.py | script | 14 KB |
External hosts referenced
www.equator-network.org www.consort-spirit.org www.bmj.com www.nature.com publicationethics.org www.ncbi.nlm.nih.gov www.prisma-statement.org www.tripod-statement.org arriveguidelines.org isac-net.org www.care-statement.org www.gensc.org www.ispor.org www.miappe.org www.psidev.info www.squire-statement.org www.strobe-statement.org arxiv.org authors.bmj.com doi.org jamanetwork.com pandoc.org www.icmje.org database.ich.org export.arxiv.org grants.nih.gov resources.equator-network.org www.amstat.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-peer-review-scan.json
- Badge for your README:
- Request a re-scan