Dynamic graph runtime for building, adapting, and observing multi-agent LLM systems in Python.
- capability exposure inferred + 22
- recent drift inferred + 12
- 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.
graded 9m ago · see ecosystem CVEs →
- B · 22 → C · 39
No known CVEs for this server.
- medium dangerous code
dynamic exec: eval()/exec()
analyzed commit d235827 · analyzer v28 · 1d ago
skills & prompt files 1
- agent-rules frontier-ai-next-gMAS-d235827/CLAUDE.md
danger signals2
- dynamic code execution eval()/exec() frontier-ai-next-gMAS-d235827/examples/agent_with_tools_example.py :67
return str(eval(expression, {"__builtins__": {}}, allowed)) - dynamic code execution eval()/exec() frontier-ai-next-gMAS-d235827/tests/test_tools_remaining.py :263
exec('def bad_func(x: "UndefinedTypeName123abc") -> None: pass', _ns) # noqa: S102
- recent drift +12 capability drift →
[](https://mcpobservatory.com/servers/github:frontier-ai-next/gMAS/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 frontier-ai-next.