The neutral standard for connecting systems to agents — Network Intent Layer (NIL) + the nilscript DSL. USB for software.
- capability exposure inferred + 35
- tool safety inferred + 5
inferred
The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.
grade last moved 1w ago · see ecosystem CVEs →
- C · 52 → C · 40
- C · 35 → C · 52
- A · 0 → C · 35
No known CVEs for this server.
- medium dangerous code
dynamic exec: __import__ sink, eval()/exec()
analyzed commit 5ed0b77 · analyzer v33 · 2w ago
skills & prompt files 1
danger signals2
- dynamic code execution __import__ sink nilscript-org-NILScript-5ed0b77/tests/test_scaffold.py :88
env={"PYTHONPATH": str(root / "src"), "PATH": __import__("os").environ.get("PATH", "")}, - dynamic code execution eval()/exec() nilscript-org-NILScript-5ed0b77/tests/test_scaffold_models.py :20
exec(compile(source, "<generated models.py>", "exec"), namespace) # noqa: S102 - testing generated code
[](https://mcpobservatory.com/servers/github:nilscript-org/nilscript/security) Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of nilscript-org.