ncats-arax
Verdict safe, but 5 findings (5 medium), mainly unauthorized tool use, data exfiltration, policy violation. Most recent scan 2026-10-21.
Second scanner: NVIDIA SkillSpector
The two scanners disagree: Cisco found nothing and SkillSpector says do not install. One of them has a blind spot here; read the skill before trusting either. How the two scanners compare across the whole corpus: Two scanners, one corpus.
What this skill does
Queries the NCATS Translator ARAX production API for bounded, typed, provenance-rich one-hop and endpoint-pinned two-hop biomedical knowledge-graph relationships. Use for Biolink-constrained RTX-KG2 lookup, explicit selected-provider ARAX federation, separate entity normalization, qualifier-aware graph traversal, and inspection of TRAPI edge bindings, publications, and knowledge-source provenance. Do not use for inference, ranking, open-ended pathfinding, clinical guidance, or sensitive queries.
- Package
- 4 files, 108 KB
- SKILL.md
- 967 words, 12+ sections
- Code
- Python (1)
- Allowed tools
ReadBash- License
- MIT
- Compatibility
- Requires Python 3.10+ and outbound HTTPS access to arax.transltr.io. The client uses only the Python standard library and needs no API key. Queries and caller metadata may be publicly visible; never submit sensitive or patient-specific content.
SKILL.md covers: NCATS ARAX · Safety boundary · Workflow · Preflight · Normalize an entity · One-hop lookup · Endpoint-pinned two-hop lookup · Selected-provider federation · Inspect saved provenance · Interpret results · Deliberate exclusions · Official references
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 Skill declares no Write tool but bundled scripts write files Policy Violationstatic
Skill restricts tools to ['Read', 'Bash'] but bundled scripts appear to write to the filesystem, which conflicts with a read-only tool declaration.
SKILL.md
MEDIUM Undeclared network usage Unauthorized Tool Usestatic
Skill code uses network libraries but doesn't declare network requirement
SKILL.md
MEDIUM Outbound network request primitives that can transmit data externally Data Exfiltrationstatic
Pattern detected: urllib.request.Request(
scripts/arax_client.py:615
request = urllib.request.Request(MEDIUM Outbound network request primitives that can transmit data externally Data Exfiltrationstatic
Pattern detected: urllib.request.Request(
scripts/arax_client.py:670
request = urllib.request.Request(What is in the package
| File | Kind | Size |
|---|---|---|
SKILL.md | doc | 8.9 KB |
references/output-schema.md | doc | 8.2 KB |
references/query-contract.md | doc | 7.7 KB |
scripts/arax_client.py | script | 84 KB |
External hosts referenced
github.com arax.transltr.io biolink.github.io ncatstranslator.github.io
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-ncats-arax-scan.json
- Badge for your README:
- Request a re-scan