exploratory-data-analysis
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
Performs bounded, local exploratory analysis of explicitly supported scientific files. Supports redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain formats are reference-only and unknown formats fail closed.
- Package
- 21 files, 206 KB
- SKILL.md
- 1656 words, 12+ sections
- Code
- Python (13)
- Allowed tools
ReadWriteEditBashGlob- License
- MIT
- Compatibility
- Bundled core CLIs require Python 3.11+ and are local/network-free; the complete pinned optional snapshot requires Python 3.12+, uv, and format-specific libraries listed below.
SKILL.md covers: Exploratory Data Analysis · Scope and non-negotiable boundary · Version baseline (verified 2026-09-30) · Exact capability matrix · Safe local I/O contract · Required EDA reasoning · Workflow · 1. Confirm authorization and root · 2. Manifest before content analysis · 3. Run the narrowest automated tool · 4. Add scientific context · 5. Create the report scaffold
Findings
No findings. SAFE
What is in the package
21 files, 206 KB. Show the list.
| File | Kind | Size |
|---|---|---|
SKILL.md | doc | 14 KB |
assets/report_template.md | doc | 7.7 KB |
references/bioinformatics_genomics_formats.md | doc | 8.8 KB |
references/chemistry_molecular_formats.md | doc | 8.5 KB |
references/general_scientific_formats.md | doc | 12 KB |
references/microscopy_imaging_formats.md | doc | 9.1 KB |
references/proteomics_metabolomics_formats.md | doc | 9.6 KB |
references/spectroscopy_analytical_formats.md | doc | 9.3 KB |
scripts/__init__.py | script | 69 B |
scripts/_capabilities.py | script | 20 KB |
scripts/_common.py | script | 14 KB |
scripts/_structured.py | script | 14 KB |
scripts/_tabular.py | script | 32 KB |
scripts/capability_manifest.py | script | 5.3 KB |
scripts/distribution_sensitivity.py | script | 3.2 KB |
scripts/eda_analyzer.py | script | 10 KB |
scripts/image_inspector.py | script | 7.7 KB |
scripts/missingness_leakage_audit.py | script | 3.8 KB |
scripts/report_scaffold.py | script | 4.1 KB |
scripts/sequence_inspector.py | script | 8.4 KB |
scripts/tabular_profile.py | script | 3.0 KB |
External hosts referenced
doi.org numpy.org www.itl.nist.gov pypi.org github.com scikit-learn.org academic.oup.com docs.python.org www.epa.gov www.fda.gov www.psidev.info ome-model.readthedocs.io arxiv.org biopython.org docs.h5py.org docs.pola.rs mmcif.wwpdb.org pandas.pydata.org pillow.readthedocs.io www.wwpdb.org anndata.readthedocs.io cclib.github.io export.arxiv.org genome.ucsc.edu iupac.org nmrglue.readthedocs.io openms.de openslide.org pyteomics.readthedocs.io userguide.mdanalysis.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
HDF5_PLUGIN_PATH
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-exploratory-data-analysis-scan.json
- Badge for your README:
- Request a re-scan