alphagenome
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
Looks up precomputed AlphaGenome Atlas effects for any GRCh38 single-nucleotide variant (AVI score with Phred and 18 SHAP feature attributions, plus raw and quantile scores for RNA-seq, DNase, ATAC, ChIP-TF, ChIP-histone, CAGE, PRO-cap, splicing, polyadenylation and contact-map tracks), scores variants or scans windows on demand with the AlphaGenome model for human and mouse (variant scoring, in silico mutagenesis, REF-versus-ALT track prediction), and builds Atlas website deep links. Use when the user mentions AlphaGenome, AlphaGenome Atlas, AVI or AlphaGenome Variant Impact, DeepMind…
- Package
- 8 files, 118 KB
- SKILL.md
- 1987 words, 12+ sections
- Code
- Python (4)
- Allowed tools
ReadWriteEditBash- License
- MIT
- Compatibility
- Python 3.10+ with the alphagenome package (0.9.0 or later for the Atlas client; brings numpy, pandas, anndata, grpcio). Network access to gdmscience.googleapis.com:443 and a free non-commercial AlphaGenome API key in ALPHAGENOME_API_KEY (ALPHA_GENOME_API_KEY also read). Human data is GRCh38 only; mouse is mm10 (model only).
SKILL.md covers: AlphaGenome and the AlphaGenome Atlas · When to use which · Setup · The coordinate contract · Atlas workflow · 1. Rank with AVI · 2. Resolve the mechanism by track · 3. Send the reader to the portal · In Python · Model workflow · Score variants the Atlas does not hold · Predict tracks and mutagenise
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 | 17 KB |
references/atlas.md | doc | 17 KB |
references/interpretation.md | doc | 8.4 KB |
references/model-api.md | doc | 14 KB |
scripts/_common.py | script | 19 KB |
scripts/atlas_link.py | script | 7.3 KB |
scripts/atlas_query.py | script | 23 KB |
scripts/score_variants.py | script | 11 KB |
External hosts referenced
github.com www.alphagenomedocs.com deepmind.google.com alphagenome.google storage.googleapis.com arxiv.org doi.org deepmind.google docs.cloud.google.com export.arxiv.org pypi.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
AVI_SCORE_FEATURE_IMPORTANCE ALPHA_GENOME_API_KEY
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-alphagenome-scan.json
- Badge for your README:
- Request a re-scan