genomic-coordinates
Verdict safe, but 1 finding (1 low), mainly unauthorized tool use. Most recent scan 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
Converts genomic intervals between coordinate conventions, normalises and compares variant representations, and detects assembly or contig-naming mismatches before they corrupt an analysis. Used whenever coordinates cross a format, tool, or assembly boundary - converting between BED, GFF/GTF, VCF, SAM/BAM, WIG, PSL, genePred, Picard interval_list, or region strings; reconciling 0-based half-open with 1-based inclusive; left-aligning or trimming indels; checking whether two variant records describe the same change; mapping genomic to transcript, CDS, or protein positions; auditing a…
- Package
- 10 files, 119 KB
- SKILL.md
- 1559 words, 12+ sections
- Code
- Python (5)
- Allowed tools
ReadWriteEditBash- License
- MIT
- Compatibility
- Requires Python 3.11+. Scripts use only the standard library - no third-party packages and no network access. Variant normalisation needs an uncompressed reference FASTA with exact contig names; .fai enables indexed access. Without .fai the entire FASTA is loaded into memory.
SKILL.md covers: Genomic Coordinates · When to use · The rule · The two conversions · Which format is which · Variants are not intervals · Check the assembly before trusting a join · Audit a file against its own format · Transcript, CDS, and protein positions · Reporting results · Verified scope · References
Findings
LOW Code uses search/grep patterns but Grep tool not in allowed-tools Unauthorized Tool Usestatic
Skill restricts tools to ['Read', 'Write', 'Edit', 'Bash'] but code uses regex search patterns
SKILL.md
What is in the package
| File | Kind | Size |
|---|---|---|
SKILL.md | doc | 12 KB |
references/format-conventions.md | doc | 12 KB |
references/reference-builds.md | doc | 7.8 KB |
references/transcript-coordinates.md | doc | 8.2 KB |
references/variant-representation.md | doc | 7.9 KB |
scripts/_common.py | script | 14 KB |
scripts/audit_intervals.py | script | 21 KB |
scripts/check_contigs.py | script | 17 KB |
scripts/convert_coords.py | script | 7.4 KB |
scripts/normalize_variant.py | script | 11 KB |
External hosts referenced
hgvs-nomenclature.org samtools.github.io github.com bedtools.readthedocs.io hgdownload.soe.ucsc.edu arxiv.org genome.ucsc.edu www.gencodegenes.org bioconductor.org crossmap.readthedocs.io daler.github.io doi.org export.arxiv.org pyranges1.readthedocs.io pysam.readthedocs.io rest.ensembl.org www.ncbi.nlm.nih.gov
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-genomic-coordinates-scan.json
- Badge for your README:
- Request a re-scan