clinical-reports
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
Creates safety-bounded draft structures and runs local deterministic checks for clinical case, diagnostic, trial, safety, and aggregate research reports. Use only with synthetic, de-identified, or aggregate inputs and verified source-fact manifests; every output requires qualified review.
- Package
- 36 files, 198 KB
- SKILL.md
- 1887 words, 12+ sections
- Code
- Python (9)
- License
- MIT
- Compatibility
- Requires Python 3.11+ for optional dependency-free local scripts. No credentials or network needed for data processing; network access is needed only to review current public guidance.
SKILL.md covers: Clinical Reports · Purpose · Non-Negotiable Boundary · Input Gate · Route Before Drafting · Safe Drafting Workflow · 1. Create a source-fact manifest · 2. Generate the correct template · 3. Populate verified fields only · 4. Run deterministic checks · 5. Apply the right review · Case Reports
Findings
No findings. SAFE
What is in the package
36 files, 198 KB. Show the list.
| File | Kind | Size |
|---|---|---|
SKILL.md | doc | 16 KB |
assets/adverse_event_aggregate_input_template.csv | data | 120 B |
assets/case_report_template.json | config | 2.1 KB |
assets/clinical_trial_csr_template.json | config | 2.6 KB |
assets/clinical_trial_results_template.json | config | 3.8 KB |
assets/clinical_trial_safety_aggregate_template.json | config | 1.4 KB |
assets/consistency_manifest_template.json | config | 531 B |
assets/deidentification_process_checklist.json | config | 2.1 KB |
assets/lab_report_template.json | config | 1.7 KB |
assets/pathology_report_template.json | config | 1.7 KB |
assets/provenance_manifest_template.json | config | 560 B |
assets/quality_review_checklist.json | config | 1.7 KB |
assets/radiology_report_template.json | config | 1.5 KB |
assets/research_summary_template.json | config | 1.6 KB |
assets/terminology_manifest_template.json | config | 426 B |
assets/trial_protocol_reporting_checklist.json | config | 4.2 KB |
references/README.md | doc | 2.2 KB |
references/case_report_guidelines.md | doc | 3.3 KB |
references/clinical_trial_reporting.md | doc | 5.3 KB |
references/data_presentation.md | doc | 4.1 KB |
references/diagnostic_reports_standards.md | doc | 4.3 KB |
references/medical_terminology.md | doc | 4.2 KB |
references/privacy_and_deidentification.md | doc | 4.8 KB |
references/professional_review.md | doc | 4.2 KB |
references/report_type_routing.md | doc | 4.4 KB |
references/safety_reporting.md | doc | 6.8 KB |
references/sources.md | doc | 11 KB |
scripts/_common.py | script | 9.5 KB |
scripts/check_deidentification.py | script | 11 KB |
scripts/consistency_checker.py | script | 13 KB |
scripts/format_adverse_events.py | script | 16 KB |
scripts/generate_report_template.py | script | 3.9 KB |
scripts/provenance_validator.py | script | 9.2 KB |
scripts/terminology_validator.py | script | 10 KB |
scripts/validate_case_report.py | script | 9.4 KB |
scripts/validate_trial_report.py | script | 20 KB |
External hosts referenced
www.fda.gov database.ich.org loinc.org www.bmj.com www.care-statement.org www.ecfr.gov arxiv.org gravitas.acr.org www.cap.org www.consort-spirit.org www.hhs.gov www.ich.org alt.meddra.org code-medical-ethics.ama-assn.org doi.org export.arxiv.org ucum.org www.cdc.gov www.icmje.org www.meddra.org www.nlm.nih.gov www.snomed.org www.wma.net
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-clinical-reports-scan.json
- Badge for your README:
- Request a re-scan