pathogen-variant-surveillance
Verdict safe, but 6 findings (5 medium, 1 low), mainly data exfiltration, 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
Queries public GenSpectrum LAPIS data for pathogen genomic surveillance, current lineage nomenclature, weekly sequence proportions, reporting delays, and descriptive mutation frequencies. Use for variant surveillance, Pango lineage validation, dominant submitted lineages, Nextclade assignment provenance, SARS-CoV-2, influenza/H5N1 clades, RSV, mpox, measles, dengue, or LAPIS queries. Distinguishes sequence prevalence from infection prevalence, clades from genotypes, missing calls from reference matches, and sampling changes from biological growth advantage.
- Package
- 9 files, 103 KB
- SKILL.md
- 1291 words, 11 sections
- Code
- Python (5)
- Allowed tools
ReadWriteEditBash- License
- MIT
- Compatibility
- Requires Python 3.11+. Scripts use only the standard library. Needs network access to public LAPIS deployments on lapis.cov-spectrum.org, lapis.genspectrum.org, lapis.pathoplexus.org and raw.githubusercontent.com for pango-designation. No credentials for these public queries.
SKILL.md covers: Pathogen Variant Surveillance · When to use · Verified scope · Workflow · Describe observed reporting delay · Discover and describe weekly proportions · Verify current names · Describe site-wise mutation frequencies · Provenance and failure handling · References · Citing Scientific Agent Skills
Findings
MEDIUM Code makes network requests Unauthorized Tool Usestatic
Skill code makes network requests. While not controlled by allowed-tools, network access should be documented and justified in the skill description.
SKILL.md
MEDIUM Outbound network request primitives that can transmit data externally Data Exfiltrationstatic
Pattern detected: urllib.request.Request(
scripts/lapis_client.py:173
req = urllib.request.Request(url, headers={"User-Agent": USER_AGENT})MEDIUM Outbound network request primitives that can transmit data externally Data Exfiltrationstatic
Pattern detected: urllib.request.urlopen(
scripts/lapis_client.py:178
with urllib.request.urlopen(req, timeout=TIMEOUT) as response:MEDIUM Outbound network request primitives that can transmit data externally Data Exfiltrationstatic
Pattern detected: urllib.request.Request(
scripts/lapis_client.py:313
req = urllib.request.Request(url, headers={"User-Agent": USER_AGENT})MEDIUM Outbound network request primitives that can transmit data externally Data Exfiltrationstatic
Pattern detected: urllib.request.urlopen(
scripts/lapis_client.py:315
with urllib.request.urlopen(req, timeout=TIMEOUT) as response: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 | 11 KB |
references/lapis-api.md | doc | 11 KB |
references/lineage-nomenclature.md | doc | 5.6 KB |
references/surveillance-caveats.md | doc | 6.1 KB |
scripts/lapis_client.py | script | 30 KB |
scripts/lineage_prevalence.py | script | 15 KB |
scripts/mutation_profile.py | script | 10 KB |
scripts/reporting_lag.py | script | 8.0 KB |
scripts/resolve_lineage.py | script | 7.4 KB |
External hosts referenced
lapis.cov-spectrum.org lapis.pathoplexus.org lapis.genspectrum.org pathoplexus.org github.com arxiv.org raw.githubusercontent.com www.who.int docs.nextstrain.org doi.org export.arxiv.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-pathogen-variant-surveillance-scan.json
- Badge for your README:
- Request a re-scan